Guard

Hierarchical planning frameworks combine skills from multiple robot control policies for long-horizon task execution, where determining when to terminate the current skill and advance to the next subtask is essential. Existing approaches often rely on pre-designed completion signal checkers that are hard to obtain in real-world execution. Large-scale vision-language models (VLMs) offer strong reasoning capabilities, but their decision boundaries are not inherently aligned with task completion criteria, while cloud deployment and lengthy reasoning introduce substantial latency, limiting real-time monitoring. We propose StageGuard, an agentic distillation framework for accurate and efficient stage-transition decisions. StageGuard combines teacher-model reasoning with demonstration trajectories to generate structured explanations of subtask completion and policy switching. A lightweight student VLM uses these explanations to generate compact self-explanations, which are used for supervised fine-tuning. We evaluate stage-transition prediction on trajectories from two benchmarks and assess closed-loop task success through integration into hierarchical robot control on BEHAVIOR-1K, with further validation on real robots. Results show substantial improvements in stage-transition prediction while supporting efficient online monitoring.

Large language model (LLM) agents interact with external environments through tool invocation, but tool outputs can also expose them to indirect prompt injection (IPI) attacks. Existing defenses mainly rely on prompt hardening, content filtering, pre-generated plans, or permission constraints. These approaches often struggle with complex tasks or over-sanitize external content, making it difficult to balance security and utility. The key challenge is therefore to preserve execution flexibility while precisely identifying and removing the malicious content that actually induces unsafe actions. To address this challenge, we propose ActGuard, a pre-execution action auditing framework. Rather than judging whether external content is inherently suspicious, ActGuard assesses whether it causes the current action to deviate from a locally reasonable expectation. At each step, ActGuard predicts the tools likely to be used by the upcoming action and constructs a local tool prior without constraining the execution trajectory. Before execution, it compares the candidate action against this prior and performs tool-level contrastive analysis and parameter-level evidence localization to identify deviations in tool selection and action parameters. A verifier then examines the localized evidence, masks only spans confirmed as malicious, and regenerates the action from the sanitized context. This design preserves legitimate planning flexibility while minimizing information loss from indiscriminate filtering. We evaluate ActGuard on challenging benchmarks for tool-using agents. Results show that ActGuard reduces attack success rates to a level comparable to state-of-the-art defenses while maintaining task utility close to the no-attack setting, achieving a favorable security-utility trade-off. Our code is publicly available at: https://github.com/binzhwang/ActGuard.

Large language models (LLMs) have been ex- ploited to generate malware, but the effective- ness of guardrails for code generation secu- rity remains unclear. We introduce CS-Guard, the first benchmark to systematically evalu- ate guardrails for code generation security. It covers 1) text-to-code generation with 1000 high-quality malware-generation prompts, 7 jailbreak attacks, and a novel fictional scenario attack (FSA) that embeds malicious intent in a legitimate fictional software-development sce- nario; and 2) code-to-code generation with 331 code prompts spanning code infilling, code completion, and code translation. We empiri- cally evaluate 9 guardrails across seven LLMs. We find that current guardrails perform poorly against malicious code-generation re- quests: for text-to-code, the average attack success rate (ASR) after jailbreaks reaches about 50% for many guardrails; for code-to- code, average ASR approaches 100% on base LLMs and remains high across many guardrails (14.4% to nearly 100%). Our FSA also achieves ASR close to 100% across many guardrails, raising major reliability concerns for real-world software development. To sup- port future research, CS-Guard uses a modular three-layer guardrail taxonomy that lets devel- opers register guardrails for evaluation. We release the benchmark and data to enable fur- ther community evaluation.

Image restoration is commonly applied before object detection under adverse conditions, yet a visually improved image need not improve the downstream task. We study this mismatch as restoration utility prediction: given a degraded image and its candidate restoration, should the restoration be used or should the original observation be preserved? We introduce TaskGuard, a post-hoc controller for frozen restoration and detection pipelines. TaskGuard characterizes the realized restoration residual through its interaction with detector sensitivity and predicts whether the intervention is task-beneficial. Exact regional counterfactuals reveal substantial within-image utility heterogeneity, while a deployable pseudo-gradient preserves statistically reliable directional information. Feature-group ablation further shows that task-conditioned evidence contributes information beyond detector-response and residual statistics. The TaskGuard utility predictor is trained only on Gaussian degradation and frozen before final evaluation, then transferred to unseen motion blur, rain, and defocus. Across these unseen families, TaskGuard reduces lossnegative interventions by 54.2% (family macro) and practical per-image detection deteriorations by 37.0% (pooled), while preserving 98.8% of the Always-Restore COCO AP. On natural-rain DAWN, it reduces loss-negative interventions by 97.9% while retaining 77.8% of the AP improvement obtained by deraining. These results support restoration utility as a task-conditioned property of the specific intervention rather than image appearance alone.

Topology-guided safeguards for LLM-based multi-agent systems (MAS) train a GNN over the inter-agent communication graph to localize risky agents and intervene on the topology---but they assume one operator can pool all labeled traces. Across organizations that assumption breaks: episodes contain private prompts, tool outputs, and proprietary workflows, and no silo alone sees the full attack distribution. We cast privacy-preserving MAS safeguarding as graph federated learning and instantiate FGLGuard: each operator fits an edge-featured graph attention detector on its own judge-labeled episode graphs and shares only model updates. The method couples a proximal local objective for non-IID clients, domain-balanced aggregation, over-refusal-constrained threshold calibration, corroborated upstream scoring, and a guarded rewrite for blocked answers. Federation is not optional: off-the-shelf transfer collapses under distribution shift (AUROC 0.51 to 0.70 only after in-domain retraining), so a deployable guard must adapt on each site's private traces. On Agent-SafetyBench, R-Judge, and AgentDojo, federated FGLGuard exceeds the in-domain centralized ceiling on all three benchmarks without pooling any data---where unsupervised anomaly guards and local-only training fail. One guard federated across four different-domain operators comes within 0.03 AUROC of multi-domain centralization, while any single-domain guard collapses on the others. Live FGLGuard cuts AgentDojo's ground-truth attack-success rate by 43% at near-unguarded utility, zero API cost, and negligible capability loss.

Complex 3D spatial text to image generation requires models to convert natural language into stable visual geometry, not merely semantic appearance. Existing prompt-driven or layout-conditioned methods improve controllability, but often lack an optimizable and verifiable spatial intermediary before visual sampling. As a result, object relations, occlusion, visibility, and camera constraints can decay during multi-round generation. This paper presents SpatialGuard, a structured layout-guided framework for complex 3D spatial text-to-image generation. SpatialGuard parses prompts into image synthesis-oriented 3D layouts through a Spatial Layout Architect, realizes them as visual conditions and candidate images through a Visual Realizer, and uses a Visual Alignment Critic to validate consistency among prompt, layout, and image. To keep constraints stable across iterations, SpatialGuard introduces a Layout Harness that organizes rule constraints, tool invocation, shared knowledge, and feedback loops around the editable layout state. This design turns complex spatial generation from implicit prompt following into a verifiable process of planning, realization, validation, and repair. Comprehensive experiments show that SpatialGuard achieves state-of-the-art performance in complex 3D spatial layout generation and improves spatial faithfulness over existing text-to-image and layout control baselines.

Skill-augmented agents load reusable skills as persistent runtime context, improving task performance but also giving malicious skills a durable channel for steering future actions. Such skills may leak secrets, corrupt code, bypass approvals, or stage data for exfiltration only after a concrete user task and workspace state make the unsafe action appear useful. This makes pre-install vetting insufficient and calls for runtime, task-conditioned protection. We propose Defense-as-Skill, a defense paradigm that implements the runtime guard itself as an installable, inspectable, and editable skill. Our guard, SkillSonar, runs alongside untrusted task skills and checks sensitive actions against the user's task boundary, routing each action to an allow, replan, or confirmation decision without modifying the underlying agent runtime. To study this setting, we construct SCOPE-R, a task-conditioned dataset covering 6 risk families and 21 sub-categories, with 206 attack-confirmed malicious instances and 43 benign tasks. We then improve SkillSonar on the SCOPE-R training subset using runtime guard-skill evolution, a Monte-Carlo Tree Search procedure that evolves the on-disk guard skill from feedback on the rollouts. Across Claude Code and OpenClaw, the evolved guard substantially reduces attack success while maintaining a favorable safety-utility trade-off. On repeated GLM-5 runs, SkillSonar reduces ID ASR from 0.482 to 0.104 and OOD ASR from 0.606 to 0.115. Further analyses demonstrate transfer across victim models, held-out risk families, and external benchmarks, as well as retained protection against adaptive attackers. Ablations further show that explicit safety responsibility assignment and the skill-native representation are both important to the observed gains.

Safety guardrails serve as the last line of defense against harmful inputs and outputs of large language models (LLMs), yet they are trained and evaluated almost exclusively on short text. We present LongGuard, a framework that evaluates, mechanistically analyzes, and mitigates long-context guardrail failure. We formulate the task as Safety Needle-in-a-Haystack (SafetyNIAH) over a 0.25k-32k length grid; across 15 mainstream guardrails, unsafe recall drops monotonically by more than 50% on average, and a paired Benign-Fill vs. Needle-Repeat design attributes the failure to proportional dilution of the unsafe needle rather than to absolute length. A three-layer attention-logit-behavior analysis on six guardrails locates the mechanism: attention mass on the unsafe needle is diluted, the unsafe-over-safe logit margin is compressed in lockstep, and the detection decision collapses accordingly, with this attention->logit->behavior chain remaining consistent after partialling out length. We further isolate a sparse set of guard-specialized retrieval heads that exhibit partial specificity relative to their base models. Building on the analysis, we propose two training-free mitigations - Chunked Detection (CD) and Attention-Head Sharpening (AHS) - and a deployment protocol, Context-Aware Hyperparameter Routing (CAHR), that selects configurations by context length and audit side. Across five benchmarks spanning synthetic data, long-context attacks, and reasoning-model outputs, CAHR-CD and CAHR-AHS improve the six-guardrail average by 22% and 13%, respectively. Code and data are available online.

Contact-rich manipulation failures are often detected only after the robot has committed to contact. This is especially limiting in wrist-camera setups: close gripper--object views help observe contact, but a poor approach may already push, miss, slip, or disturb the object before conventional detectors react. We introduce \emph{ContactGuard}, a pre-contact execution monitor for chunked visuomotor policies. Given the policy's planned action chunk, ContactGuard predicts its short-horizon consequence in latent visual space and aborts if the predicted future latent indicates likely failure. Its latent world model is trained from unlabelled robot trajectories to predict compact multi-view visual embeddings under planned actions, avoiding pixel-level video prediction. A lightweight failure probe is then trained from a small labelled set of pre-contact clips. At deployment, ContactGuard anchors prediction before an imminent contact event, rolls the model forward under the policy's own actions, and verifies the predicted post-contact latent. Across real-world contact-rich manipulation tasks, ContactGuard predicts failure more accurately than direct and corrupted-action ablations, and transfers to live robot as a pre-contact abort signal without modifying the underlying policy.

Diffusion-based vision-language-action (VLA) policies can generate plausible actions even when their predictions are weakly grounded in the visual and language evidence defining the task. We introduce GUARD, a test-time failure detection method that measures this grounding without modifying the pretrained policy. GUARD estimates the influence of token-indexed entries in the final vision-language model key-value (KV) cache, constructs counterfactual caches by ablating salient KV entries, and compares their denoising responses with the original conditioning. Based on the comparison, we derive GUARD diagnostic stream including sensitivity, attention entropy, modality bias, and grounding efficiency, which are calibrated online and processed by a lightweight temporal classifier. We evaluate GUARD under task-held-out splits across five policy-benchmark settings, using Pi0, SmolVLA, and Alpamayo-1.5 on LIBERO, SimplerEnv, MetaWorld, and PhysicalAI-AV. GUARD achieves the best ROC-AUC on four of five unseen-task settings and ranks second on the remaining setting, improving the average unseen-task ROC-AUC by 5.73 percentage points over the strongest competing runtime monitor while remaining within 0.19 points of the best seen-task average. These results show that directly probing action-head dependence on multimodal evidence provides a transferable failure signal across policies, tasks, embodiments, and domains.

Reasoning-based guard models improve LLM safeguards, but decoding explicit rationales for every interaction makes them costly to deploy. Although latent-reasoning methods reduce token generation by moving reasoning into continuous states, they remain underexplored for safety moderation and lack an inspection interface for deployment. In this paper, we propose LatentGuard, an efficient and inspectable safeguard framework that brings continuous latent reasoning to guard models. LatentGuard uses a staged curriculum to progressively compress task-aligned textual rationales into compact latent states, enabling safety verdicts to be predicted directly from continuous representations. To preserve inspectability, an isolated auxiliary decoder generates compact audit artifacts on demand, keeping rationale generation off the standard inference path. Experiments show that LatentGuard-8B improves mean weighted F1 from 83.95 to 84.91 over GuardReasoner-8B, while reducing critical-path reasoning cost from 268.56 generated rationale tokens to 1.60 latent reasoning tokens. Its audit decoder achieves an audit utility score of 85.75, demonstrating an efficient and inspectable path toward deployable LLM safeguards.

Safety guards are widely used to filter harmful content and are typically trained via supervised fine-tuning on labeled prompt-response pairs. We audit two widely used safety-guard training datasets, WildGuardMix and GR-Train, and find that among responses to harmful prompts, refusal expressions co-occur almost exclusively with unharmful labels. This imbalance motivates what we term the refusal-cue shortcut: inserting a refusal cue into a harmful response could flip the guard's verdict from harmful to unharmful. The shortcut affects not only guards trained on these datasets but also officially released models such as LlamaGuard3 and Qwen3Guard whose training data is undisclosed. It persists across response positions and is generally stronger in smaller variants within a family. To mitigate it, we adapt sparse complementary masking as a lightweight post-hoc intervention that identifies and suppresses a small set of shortcut-associated attention heads and MLP neurons without retraining. On two primary benchmarks, the intervention achieves an approximately 79% relative reduction in response-initial detection failures induced by refusal cues, while preserving standard detection performance. Although optimized using cues at a single response position, the suppression effect transfers to unseen positions and datasets, suggesting that shortcut manifestations across positions are partly mediated by shared internal components. Further analysis provides evidence that shortcut reliance and legitimate refusal recognition are partially functionally separable, as suppressing the shortcut broadly preserves the guard's ability to recognize genuine refusals.

LLM-based multi-agent systems (MAS) increasingly rely on persistent private and shared memories for long-horizon coordination. This memory layer improves continuity, but it also gives attackers a durable channel: a poisoned memory can be written once, continuously retrieved in later tasks, promoted into shared memory, and reused by other agents. A single poisoned write can therefore steer many later decisions and contaminate agents that never saw the original attack, all while no malicious message crosses a visible communication edge at the moment of harm. Further, because existing safeguards mainly inspect prompts, actions, or communication edges, they can miss attacks whose content appears benign at write time but becomes harmful after retrieval. We introduce Memory-Aware Propagation and Link Enforcement Guard, MAPLE-Guard, a memory-link guard for memory-enabled MAS. MAPLE-Guard monitors the memory lifecycle and places gates at write, retrieval, promotion, and cross-agent reuse, so risky memories can be quarantined, unsafe retrievals filtered, and poisoned private memories blocked before they enter shared memory. In the main evaluation, MAPLE-Guard lowers attack success rate (ASR) from 38.2% to 0.9% on LongMemEval and from 34.7% to 0.2% on AppWorld; it also raises multi-agent defense success rate (MDSR) from 54.0% to 74.3% and from 42.5% to 99.8% on the same benchmarks. These results suggest that memory-aware link enforcement covers a gap left by prompt-level and topology-level defenses. Code is available at the link: https://github.com/xiong-wenjun/MAPLE-Guard.

Conflicting objectives are general in RL alignment, and training on them data-efficiently is hard. Training a safety guard with RL means optimizing two objectives that conflict: catch real harm, and do not refuse benign prompts. Our finding is that over-refusal improves 22.4% to 12.8%, while under-refusal on adversarial attacks silently worsens 0.27 to 0.33. We present C-Guard, a constitution-grid instrument that generates the RL training data, and C-LIM, a per-cell learnability score that decides each cell's move: prune, densify, amend, expand. C-LIM flags the dead-weight data region before any training budget is spent: 187 untargeted rows had bought zero gain, and our method lifts the same region's learning impact 0.733 to 0.80. Code and the constitution are open-sourced.

Safety classifiers ("guards") are the dominant black-box defense for vision-language models, yet a guard judges an input's surface form, not its meaning: a harmful request re-encoded as set theory, formal logic, a classical language, code, or text rendered inside an image slips past a guard that would block it in plain language - the decode gap. The standard fix is a preprocessor that recovers image content and decodes the encoding before the guard. We build one and evaluate it against an ensemble of eleven published encoding attacks, counting a behavior as broken if any attack succeeds. That metric separates two mechanisms such defenses conflate. Restoring a view the guard never had improves it on both axes at once: it blocks far more attacks, and, measured on a category-balanced benign set, it blocks fewer benign requests, because restating a request normalizes the borderline phrasing a classifier over-flags. It still does not make the system safer: against an attacker free to choose among eleven encodings, closing one channel relocates the success rather than removing it, and no ensemble contrast survives multiple-comparison correction. What does lower ensemble attack success is re-screening the recovered pre-decode surface, and that step is where the entire benign cost falls. The safety-utility trade-off is therefore not a property of recovery; it is localized to one step. Across the full guard x target x condition factorial, no configuration reaches an ensemble attack-success rate at or below 40% while holding benign over-refusal under 70%. The per-attack averages usually reported understate the attacker roughly fourfold, which is why this frontier is easy to miss. Composing across defense families is the one lever that moved the safety axis, beating every configuration we measured, and still landing far outside any deployable refusal budget.

The rapid development of large language model (LLM) agents has enabled their broad adoption across diverse real-world tasks. To standardize interactions between LLM agents and external environments, Model Context Protocol (MCP) tools have emerged as a de facto standard and have been widely integrated into these systems. However, the use of MCP tools also introduces new safety risks, as LLM agents can be induced to perform malicious or unauthorized actions. Although prior work has proposed defenses for securing tool use in LLM agents, most methods rely on static analysis, i.e., inspecting prompts and generated outputs, which limits the defense effectiveness and robustness. To address these limitations, we propose MTGuard, a hybrid analysis-based defense framework designed to safeguard the use of MCP tools in LLM agents by leveraging lifecycle-aware static-dynamic co-analysis. Extensive evaluation demonstrates that MTGuard effectively mitigates multiple categories of harmful tool use across different LLM agents while maintaining performance on benign user tasks.

What did it take for Hermes, the devout messenger of the Olympian gods, to slay Argus Panoptes, the multi-eyed giant of Greek myth? As the perfect guardian, Panoptes' legion of ever-watchful eyes proved difficult -- but not impossible -- to defeat. The centerpiece of Hermes' strategy was obfuscation and sabotage. Posing as a shepherd, Hermes sealed each of Panoptes' eyes -- eyes that would otherwise have alerted the fearsome giant to Hermes' plot -- and vanquished him. The moral of the story: when a challenger must surmount a formidable foe -- one far greater in stature and vastly more equipped -- crafty maneuvers are not merely advisable but indispensable for victory. In this work, the "challenger" is a collective leveraging adversarial tactics to overcome the "multi-eyed giant" of stylometric systems and surveillance apparatuses. To successfully claw back the privacy siphoned by the multi-eyed giant, the challenger must carefully evaluate their plan of attack, $\textit{TraceTarnish}$, and determine what does and does not work to anonymize the authorship of text. To that end, we conduct an ablation study of $\textit{TraceTarnish}$ to better understand which module -- Translation, Obfuscation, Imitation, or Injection -- best confounds a stylometric system. Our results indicate that the most effective approach was Injection, meaning that inserting zero-width Unicode characters, homoglyphs, and intentional misspellings neutralizes the indefatigable eyes long enough to claim the head of the all-seeing giant.

Automated sleep staging is increasingly used in large-scale studies to derive sleep-architecture endpoints: total sleep time, REM latency, sleep efficiency, and bout-duration statistics. Deep learning models achieve epoch-level accuracy approaching inter-rater agreement, yet often produce hypnograms that violate physiological invariants, such as rare transitions (e.g., direct Wake -> REM) or excessively fragmented sequences. Such violations can bias downstream sleep metrics, regardless of overall accuracy. We propose StageGuard, a plug-and-play, backbone-agnostic structured-inference framework that wraps any neural sleep-staging backbone with physiology-informed priors. StageGuard combines (1) a differentiable soft transition penalty that discourages physiologically rare transitions during training, and (2) a semi-Markov constrained decoder with a duration-augmented state space that jointly enforces transition penalties and minimum bout durations at inference. Unlike hard-prohibition methods, it admits rare transitions when emission evidence is overwhelming, leaving informative pathological events recoverable rather than blocked. StageGuard constrains staging outputs to satisfy known physiological priors rather than modeling sleep generatively. We quantify the validity gap using transition-violation rate (TVR) and fragmentation index (FI) and demonstrate that, across six backbones and four datasets, StageGuard reduces TVR to physiologically plausible levels and lowers FI by 56-62%, while maintaining or slightly improving classification accuracy. Crucially, improved constraint satisfaction translates into 59-79% lower error on derived sleep-architecture statistics not directly optimized by the method, and recovers the direction and effect size of expert-defined subgroup differences (OSA severity, age) more faithfully than the unconstrained baseline.

LLM agents increasingly rely on external tools, expanding capability while creating a new security boundary: third-party tools may appear benign at the interface level while embedding unsafe behavior in implementation. Existing defenses rely on weak metadata, collapse characterization and policy judgment into a single decision, or use heuristic/LLM enforcement that lacks deterministic, auditable reasoning over task context and multi-tool composition. This paper presents ToolGuardian, a policy-driven framework for securing agent-tool interactions through pre-admission vetting and task-aware runtime authorization. ToolGuardian uses progressive characterization to convert evidence into structured facts: descriptions capture declared intent, system-call traces expose coarse behavior, mock execution reveals observed effects, and source analysis identifies latent behavior. ToolGuardian's core contribution is an Answer Set Programming (ASP)-based declarative policy layer that reasons explicitly over capabilities, effects, task context, and composition. We compare ASP against heuristic and LLM-based policy realizations using identical inputs and output contracts. We evaluate ToolGuardian on 16 MCP-style tools, including 8 malicious variants derived from real open-source tools, and 20 runtime scenarios. For vetting, ASP reaches a deny-class F1 of 0.86 and 88% accuracy using description, syscall, and observed-effect evidence. For runtime authorization, fully specified realizations classify all scenarios correctly, while ablations show that removing compositional and conformance rules substantially degrades performance.

A vision-language AI assistant returns its answer as a stream of generated tokens. Therefore, a safety guard that watches that answer has to keep up with the stream and stop a harmful reply before a user reads it. Recent vision-language guardrails instead generate a chain of thought before they issue a verdict. They believe that step-by-step reasoning yields a safer guard. This design makes the guard heavy and slow, since the model must decode many tokens for harmfulness detection. We pose the question of whether a vision-language guard really needs to reason in order to screen a response. We answer with a guard that has no chain. ResponseGuard reads a harmful verdict from a single pooled representation of the request, the response, and the image in one forward pass. Across a standard multimodal guardrail benchmark, our 2B ResponseGuard outperforms a recent 3B reasoning-based vision-language guard on response harmfulness detection, without any reasoning and at about 150 times lower time cost. On request harmfulness the reasoning guard retains an overall lead, and the remaining gap on both tracks sits on the image-only cells. We observe that the gap may stem from the frozen vision encoders that both designs use rather than from the missing chain. We have also found the reasoning guard directs almost none of its verdict attention to the image. Based on a single-pass detection, ResponseGuard can screen an answer sentence by sentence as it streams and stop a harmful answer before it finishes. For guarding the response of a vision-language model, a calibrated single-pass label may provide a sufficient safety signal. We fully release all source code, trained models, and datasets at https://github.com/ndb796/ResponseGuard.

Agent safety is moving from content moderation toward preventing operational failures before tool-using agents act. We propose Janus, a foresight-oriented framework for long-horizon agent safety that trains guards to anticipate delayed risks from partial trajectories. Janus synthesizes diverse agent trajectories via multi-agent simulation and learns a shared policy with two coupled tasks: an anticipation task that forecasts safety-relevant futures and an adjudication task that decides safety from both the observed prefix and anticipated future. The two tasks are jointly optimized with CoAA-RL, which rewards forecasts by their utility for downstream safety judgment. The resulting guard model, Vanguard, blocks unsafe actions before execution. Across four agent-safety benchmarks, Vanguard improves average protection by 15.9 percentage points over baseline guards while increasing benign task completion by 5.1 percentage points.

Multi-agent LLM applications chain a planner, worker agents, a verifier, and a synthesizer, and every hop between agents is an unmonitored channel through which an adversary can smuggle instructions. Existing defenses guard only the input boundary (IBProtector, Llama Guard, perplexity filters, SmoothLLM) or run outside the application as opaque, stochastic provider-side filters. We show this gap carries a consequence rarely measured: on a 2,100-trace evaluation across eight attack families, five defenses, and three model backends, an undefended pipeline that appears fully safe under standard reporting (attack success 0.000 on tool- and memory-poisoning) owes that safety almost entirely to the cloud provider's server-side filter (54 of 60 blocks on Azure GPT-5), and silently shifts to the agent model's own alignment on a backend without such a filter. Outcome-only reporting hides this dependence. We present ChannelGuard, a training-free defense-in-depth framework placing information-bottleneck gates on every inter-agent channel; each scores channel text against an adversarial phrase bank by embedding similarity and deterministically passes, compresses, or blocks it, adding no LLM call, while an attribution method records which layer stopped each attack. ChannelGuard's tool-output gate blocks Tool Poisoning 30 of 30 at the application layer, identically across Azure GPT-5, Anthropic Sonnet 4.5, and Anthropic Haiku 4.5, whereas the undefended pipeline shifts entirely across backends; it also lowers Prompt Injection attack success by half (0.333 to 0.167) and preserves GSM8K accuracy exactly (0.867). White-box adaptive paraphrase evades every embedding gate, where a perturb-and-vote baseline does better. An extended appendix adds baselines, ablations, sweeps, a benign-preservation analysis, and a judge audit (kappa = 0.900), at a total cost of 47.36 USD.

Multi-view spatial reasoning requires vision-language models to compare visual evidence across images, align object correspondences, and infer spatial relations over long visual contexts, a setting where chain-of-thought reasoning tends to grow verbose without becoming more accurate. Reinforcement learning with verifiable rewards is a natural fit for this task, but standard GRPO reward relies on sparse outcome-level feedback and gives no signal about where a reasoning trajectory goes wrong, nor any control over its length. We propose LenGuard-GPC, a dense reward framework that addresses both problems together. For each sampled trajectory, it compares the token-wise predictive distributions under a standard prompt and a guided prompt, and uses the resulting token-sum KL divergence as a dense reward signal. Since this KL penalty accumulates over tokens and would otherwise reward shorter responses regardless of their quality, we introduce a staged length bonus that keeps reasoning length within a controlled range without simply encouraging brevity. On six multi-view spatial reasoning benchmarks, LenGuard-GPC improves accuracy over vanilla GRPO while reducing average response length.

LLM agents can leak privacy (e.g., paths, emails) and credentials (e.g., API keys) as agent observations (e.g., tool outputs, shell logs, and file reads) are appended to provider-bound transcripts. Existing placeholder redaction is brittle: it can miss embedded or cross-turn references, over-redact benign lookalikes, and destroy the structure useful for reasoning. We present SlotGuard, a local transcript boundary that can hide sensitive data while retaining agents' performance. SlotGuard rewrites structural bindings as typed, suffix-aware slots, replaces secrets with format-preserving synthetic values, links cross-turn references with a lightweight session graph, and restores raw values only inside the trusted runtime. On controlled repository-oriented agent transcripts, SlotGuard removes all 20,814 annotated structurally sensitive characters across 9,229 paths and reduces credential leakage to 0.0% across 852 planted values. It remains close to raw-transcript task success across four upstream models, while generic redaction drops to 2.5%. Transcript rewriting takes a median of 14.424~$μ$s per agent turn. The code is publicly accessible at https://github.com/illinoisdata/SlotGuard.

Communication-limited robots in mission-critical scenarios such as disaster inspection and search-and-rescue must make reliable onboard decisions without access to remote operators or high-capacity reasoning services. Episodic memory reuse is an attractive low-cost fallback, but retrieval similarity does not guarantee execution validity, i.e., a retrieved action may match the current context yet be unsafe due to changed topology, insufficient battery margin, or unreliable prior outcomes. We call such high-similarity but execution-invalid episodes memory traps. This creates a safety-efficiency design space where similarity only reuse minimizes fallback cost but can be unsafe, while always invoking local reasoning improves safety at high computational and energy cost. This paper presents MemoGuard, a lightweight adaptive runtime that validates episodic memories against topology, resource, and outcome contracts before reuse, invoking fallback only when validation fails. In a graph-based corridor-inspection simulator, MemoGuard reduces battery safety violations by 76.6% over similarity-only top-1 reuse while reducing fallback calls by 21.4% over always reasoning. On an NVIDIA Jetson AGX Xavier with local llama3.2:3b fallback reasoning, this corresponds to 3.67 s and 36.97 J of avoided fallback-reasoning overhead per trial. We open-source MemoGuard at https://github.com/hetheiin/memoguard.

Mobile graphical user interface (GUI) agents have demonstrated remarkable capabilities in automating complex tasks, yet they introduce critical safety risks because a single erroneous action can lead to irreversible consequences. Existing safety mechanisms are primarily reactive, lacking the ability to assess risks before execution. In this paper, we introduce SeerGuard, a consequence-aware safety framework designed to mitigate these risks through pre-execution instruction-level screening and action-level risk assessment. Specifically, the action-level assessment analyzes agent-proposed actions within current GUI states, anticipating likely outcomes to identify risks before they are executed. To enable these capabilities, we construct a unified safety-augmented world model (SAWM) via multi-task learning, integrating semantic next-state prediction with safety risk assessment. Extensive experiments demonstrate that SeerGuard generalizes effectively across diverse mobile GUI agents. On Qwen3-VL-8B-Instruct, it increases the safety-utility score from $0.191$ to $0.596$ at $ω=0.8$ and reduces the risk-cost score from $0.347$ to $0.135$ at $α=0.8$. Further analyses on our SAWM validate the effectiveness of the instruction-level screening, alongside the capability of action risk assessment and next-state prediction.

LLM agents act on real-world environments through tool calls, and a single misjudged action can cause irreversible harm. The standard safeguard is a guard model that labels each proposed action as safe or unsafe, but this binary view conflates two distinct decisions: whether the action is harmful in itself, and whether it is appropriate given the user's context. It also operates at the granularity of action categories rather than individual instances, producing routine interruptions that erode autonomy and train users to wave through the most consequential alerts. We reframe the problem as a per-instance three-way routing decision over {EXECUTE, ASK, REFUSE} and instantiate it with Safety Sentry, a lightweight guard model whose inference reduces to a single decoding call. A single decoding-time threshold lets one fixed checkpoint be re-positioned across deployments of differing risk tolerance without retraining. Safety Sentry outperforms a broad set of open-weight and frontier closed-source baselines on overall accuracy and safety-related recall, while controlling both directional error rates simultaneously.

Large language models deployed in open-world applications require safety guardrails that are both robust to complex risks and efficient enough for low-latency runtime moderation. Existing guardrails face a practical trade-off between lightweight classification-based models, which are efficient but often struggle with concealed intent, ambiguous semantics, and borderline safety decisions, and reasoning-based guards, which improve judgment quality but introduce additional token generation and inference latency. We present DT-Guard, a content safety guardrail model based on a Reasoning-Active Training, Reasoning-Free Inference paradigm. The key idea is to use reasoning supervision during training while emitting only structured safety labels at inference time. DT-Guard formulates safety judgment as a progressive decision process, Intent - Category - Safety, and constructs an intent-driven dataset with intent labels, risk categories, safety labels, and structured reasoning trajectories. To further improve hard-case robustness, we propose Rollout-Guided Progressive Hard-Case Optimization (RG-PHO), which uses multi-rollout consistency to identify stably mastered, persistently failed, and preference-unstable samples, and applies targeted supervised and preference optimization accordingly. At inference time, DT-Guard directly generates structured labels without explicit reasoning traces, preserving deployment efficiency. Experiments on prompt-side and response-side safety benchmarks show that DT-Guard achieves average F1 scores of 0.886 and 0.870, respectively. With only a 4B backbone, it reaches a dual-side average F1 of 0.878, outperforming strong 8B guardrail baselines. These results demonstrate that reasoning supervision can be effectively internalized into low-latency safety discrimination.

Large language models (LLMs) are increasingly deployed in domains requiring guardrails to detect unsafe, off-topic, or adversarial prompts. Existing guardrails predominantly rely on fine-tuning to build classifiers, which often suffer from low generalization and high inference latency. We present kNNGuard, a training-free guardrail that utilizes the activation space of an off-the-shelf LLM. Given a small bank of 50 safe and unsafe prompts, kNNGuard extracts hidden activations and performs multi-layer kNN fusing activation-space and embedding-space scores for classification. Across six domains spanning topical and security prompts, kNNGuard achieves competitive or superior F1 compared to fine-tuned state-of-the-art guardrails while running 2.7x faster than the best comparable guardrail, and 10x faster than a fine-tuned safety classifier without gradient updates or fine-tuning. Domain adaptation requires only updating the labeled bank, which can be constructed in under 10 seconds and several orders of magnitude faster than established guardrails. We also analyze the impact of system prompts, layer selection, and integration into production LLM pipelines as a configurable, low-latency guardrail.

As Large Language Models (LLMs) are increasingly deployed in healthcare settings, accurate error detection and correction in generated or existing text becomes critical, as even minor mistakes can pose risks to patient safety. Existing methods for error detection and correction, including automated checks and heuristic-based approaches, do not generalize well across unseen datasets. In this paper, we propose MedGuards as a medical safety guardrail, which is a new framework that treats medical error detection and correction as a multi-agent in-context learning task. Specialized agents separately detect, localize, and correct errors, while a confidence-guided arbitration mechanism resolves disagreements using reasoning traces and confidence scores. This design enhances interpretability, robustness, and adaptability, without requiring additional training of the base LLMs. Additionally, we introduce the Keyword-Prioritized Correction Score (KPCS), a new evaluation metric that considers whether critical keywords within the reference text are generated correctly, providing a more comprehensive assessment than conventional metrics. Experiments across four multilingual medical datasets consisting of clinical notes demonstrate significant improvements by the proposed framework across several metrics and models. Our aim is to enable safer deployment of LLMs in real-world healthcare applications. For reproducibility, we make our code publicly available at https://github.com/congboma/MedGuards.

Vision-language models (VLMs) are increasingly deployed in consumer, medical, financial, and enterprise applications. This broad deployment expands the safety surface: risks can arise from multimodal question answering, assistant responses, and cross-modal composition, while moderation policies may vary across products, regions, and deployment stages. Most existing guardrails either rely on fixed taxonomies or target only a narrow set of interaction settings, which limits their adaptability when safety rules change at deployment time. We present \textbf{SingGuard}, a policy-adaptive multimodal guardrail model family for safety assessment in multimodal conversations. SingGuard treats the active policy as a runtime input: given natural-language rules, it checks the target content against the active policy rule by rule and predicts both the safety label and the triggered rule. To balance efficiency and interpretability, SingGuard supports fast, hybrid, and slow inference regimes along a fast-to-slow reasoning spectrum, ranging from direct safety judgments to policy-grounded deliberation. We further optimize this behavior with fast--slow decoupled reinforcement learning. We also introduce \textbf{SingGuard-Bench}, a multimodal guardrail benchmark with 56{,}340 examples spanning 80+ fine-grained risk types across multimodal QA, adversarial attack, and dynamic-rule evaluation settings, including cross-modal joint-risk cases where each modality is harmless in isolation but their composition implies unsafe intent. Across six benchmark families (35 datasets), SingGuard achieves state-of-the-art average F1 in every family. Dynamic-rule evaluation further shows improved policy-following accuracy from 0.6465 to 0.7415 under runtime policy shifts. Our code is available at https://github.com/inclusionAI/Sing-Guard.

Ensuring safety of learning-enabled robotic manipulation across diverse embodiments and tasks still requires significant manual engineering. Existing approaches typically rely on heuristically designed fallback controllers or complex forward invariance assessments. These methods are often too conservative for task success, too computationally expensive for real-time execution, too heuristic to provide useful safety guarantees, or too engineering-heavy to transfer between setups. In this paper, we propose a universal safeguarding approach, X-Safe, which reasons directly in the robot's configuration space to provide formal probabilistic guarantees for collision avoidance. By operating in the configuration space, our method transfers across embodiments while relying solely on an object-based, quasi-static scene representation and a forward kinematics model of the robotic manipulator. Thus, X-Safe provides useful formal safety guarantees without requiring additional data, or engineering effort for different embodiments or scenes. We demonstrate X-Safe for diverse embodiments and policies, both in simulation and on hardware. We observe less degradation in task performance compared to state-of-the-art safeguarding, no collisions on hardware experiments, and empirically corroborate our formal guarantees.

Federated Learning (FL) in surgical video AI enables collaborative model training without sharing sensitive data. However, standard evaluation practices - selecting the "best" global model based only on validation data from participating hospitals - can lead to suboptimal deployment choices. We identify this critical failure mode as performance leakage, where the selected model overfits internal federation data and fails to generalize to unseen institutions. We propose GEN-Guard, a practical post-hoc framework to detect and correct generalization failures in federated surgical AI. It integrates Generalization Detection via Client-Blocked Evaluation (CBE), which validates performance on isolated client distributions to prevent performance leakage, and Generalization Correction through Disagreement-Aware Distillation (DAD), which learns adaptive feature-level corrections for cross-institutional robustness. Both components operate after standard FL convergence while providing robust support for zero-shot adaptation to unseen environments. We first quantify the severity of performance leakage, observing Model Selection Failures (MSFs) exceeding 80% under standard evaluation. GEN-Guard is evaluated on two multi-center clinical challenges: surgical phase recognition in laparoscopic cholecystectomy and polyp segmentation in colonoscopy. Across both datasets, GEN-Guard consistently corrects these failures, improving in-federation F1 scores by up to 2 points, unseen-institution performance by up to 3 points, and worst-case institutional performance by 3-9 points. Performance leakage represents a systematic and previously under-recognized risk in federated surgical AI. GEN-Guard provides a practical solution for detecting and correcting such failures. By improving cross-institutional robustness and zero-shot generalization, it strengthens the reliability of FL for real-world surgical deployment.

Web navigation requires agents to follow natural language goals, interact with web pages, and produce accurate answers. While recent advances leverage vision-language models and reinforcement learning, existing methods still suffer from single-step fragility due to reward misalignment and error propagation. To tackle the reward entanglement, we design Dynamic Dual-Policy Optimization (DDPO), which dynamically switches between a navigation-first mode for exploration and an answer-first mode for question-answering to mitigate reward conflict. To calibrate the single-step error, we propose Confidence-Guided Adaptive Navigation Reflection (CANR), a mechanism that estimates per-step confidence, triggers reflection only when necessary, and uses contrastive rewards to encourage self-correction to calibrate the single-step inaccuracy. With the above as the main components, we finally develop our StepGuard, a new framework of Guarding Web Navigation via Single-Step Calibration. Experiments demonstrate that our approach significantly improves navigation and answer accuracy, setting new state-of-the-art performance on standard web navigation benchmarks.

The widespread deployment of face recognition (FR) systems exposes personal images shared on social media and public platforms to identity linkage and privacy risks. Existing adversarial privacy protection methods can degrade unauthorized FR performance but are not compatible with generative face editing. Artificial intelligence-driven face editing tools are gaining popularity, which has significantly increased user demand for personalized portrait generation and social sharing. However, current editing methods often preserve identity features, making the edited images still susceptible to tracking by malicious FR systems. Thus, this paper proposes Flux-Guard, a privacy-preserving face editing framework based on adversarial attacks, which integrates face editing and privacy protection within a unified generative process. Specifically, we design a flow trajectory control method to align semantic manipulations with the generative process and introduce latent-space adversarial optimization with an adaptive perceptual-loss-driven weighting strategy, dynamically adjusting adversarial strength to maximize attack effectiveness while preserving visual quality. Extensive experiments demonstrate that Flux-Guard supports face editing while significantly improving attack success rates against cross-domain face recognition models on the CelebA-HQ and LADN datasets. Furthermore, evaluation results for commercial APIs have confirmed its effectiveness in real-world applications. The code is released at https://github.com/JLMWang/Flux-Guard.

Proactive warning is an important capability for edge intelligent services, where the system predicts whether a subject will successfully complete an incoming task under strict latency and privacy constraints. Such prediction depends on both long-term static attributes and short-term dynamic states derived from historical interaction logs. Recent Large Language Models (LLMs) offer strong long-context reasoning for constructing structured profiles from these logs, but existing solutions face two challenges for edge deployment: (1) profiling methods are typically domain-specific and lack a reusable abstraction across service scenarios, and (2) fine-tuning alignment models on heterogeneous edge clusters incurs high synchronization overhead due to the variance in input sequence lengths. To address these challenges, we propose CogGuard, a proactive-warning framework for edge intelligent services. CogGuard decouples offline LLM-based profile construction from online Small Language Model (SLM)-based score prediction through a shared static-dynamic profile-to-score pipeline, and instantiates it in two representative scenarios: educational performance warning and operational task outcome warning. For efficient profile construction, we design scenario-specific profiling methods with prefix-aligned KV-cache reuse to reduce repeated encoding overhead. For edge-side model alignment, we propose a length-aware distributed fine-tuning strategy with contrastive regularization to mitigate workload imbalance on heterogeneous clusters. Experiments on education and operation datasets show that CogGuard reduces profile construction time by up to 48% and distributed fine-tuning time by 19%, while achieving MAEs of 13.4 and 5.9, respectively, on 100-point-scale warning tasks. In the largest educational setting, CogGuard reduces prediction error by 15.4% compared with the strongest baseline.

Screenshot-based mobile GUI agents can operate ordinary smartphone apps through the same visual interface as a human user, but this capability also turns every screen observation into a privacy boundary. During normal task execution, screenshots may expose contacts, messages, photos, files, recommendations, health cues, and other sensitive context that is unrelated to the user's request. We call this problem incidental visual privacy exposure. It is difficult to address with existing defenses: text anonymization misses many visual and inferential cues, while generic privacy masking can remove the evidence and controls that a GUI agent needs to complete the task. This paper presents CAPED, a context-aware pre-upload exposure control layer for mobile GUI agents. CAPED is designed as a phone-side protection layer: before screenshots are released to a remote multimodal agent, it extracts task requirements, uses screen context as a privacy prior, parses visible UI elements, and selectively exposes only content needed for the current task while masking incidental private content. We evaluate CAPED on AndroidWorld for broad task utility and with a controlled 28-task seeded privacy evaluation used as a measurement instrument for trajectory-level incidental leakage. In this seeded evaluation, Full CAPED reduces success-conditioned weighted seeded leakage from 0.766 under raw screenshots to 0.268 while preserving high task utility. A broader AndroidWorld run shows a remaining prototype-level utility cost, but the results show that task-driven selective exposure can reduce incidental visual leakage before screenshots are released to a remote GUI agent.

Deploying safe large language models (LLMs) on resource-constrained edge devices presents a critical challenge: while dual-model systems combining LLMs with guard models provide effective safety guarantees, their substantial memory and computational demands make them prohibitively expensive for on-device deployment. This paper presents a comprehensive study of parameter-efficient safety alignment methods for resource-constrained settings. Through systematic evaluation across multiple LLM architectures, training objectives, and parameter-efficient fine-tuning approaches, we identify that soft prompts combined with distillation-based training consistently outperform alternative methods. We introduce distillation frameworks based on total variation and KL divergence that effectively transfer safety behaviors from guard models into learned soft prompts. Our evaluations on various benchmarks demonstrate that this combination achieves superior safety-usefulness trade-offs compared to LoRA adapters, steering vectors, and direct optimization methods, while requiring minimal additional memory and compute at inference time. These findings establish soft prompt distillation as the preferred approach for safety alignment in on-device LLM deployment.

Artificial Intelligence (AI)-based Intrusion Detection Systems (IDS) deployed in energy infrastructure are vulnerable to model theft attacks, which allow adversaries to create evasive traffic offline. Current defences against model extraction rely either on identity-bound query monitoring, which is ineffective against distributed attackers (Sybil), or on prediction poisoning through soft-label perturbation, which is inapplicable to hard-label IDS deployments. Therefore, we propose FlowGuard, an identity-independent defence based on flow matching that classifies incoming queries as out-of-distribution (OOD) prior to IDS processing. This approach exploits the fact that queries generated synthetically for data-free model stealing attacks occupy a lower-dimensional manifold than real network traffic. This results in measurably lower log-likelihoods when using a Continuous Normalizing Flow that has been trained on legitimate data. We evaluate our method against PRADA and FDINet using MAZE and DisGUIDE attacks in single-client and distributed (100-client Sybil) settings. While PRADA's detection rate dropped to 0% when the distribution changed, our defence maintained a stable detection rate across both settings without relying on identity information. We discuss the scope and limitations of the approach, and outline potential applications to data-dependent attacks.

Large language models (LLMs) are increasingly used for knowledge base question answering (KBQA), where answering requires selecting entities from a question-specific knowledge-graph subgraph. Yet LLMs are known to hallucinate across tasks, and KBQA is no exception: even when we provide a graph as the knowledge source, the model may rely on parametric knowledge instead of graph evidence or perform invalid reasoning over the given relations. Such hallucinated answer nodes can limit the practical deployment of KBQA systems, especially in high-stakes domains such as healthcare. We formulate hallucination detection in KBQA as an answer-node classification problem and propose a lightweight graph-based framework that treats the answering LLM as a black box. \methodname represents each KBQA instance as an augmented graph. It initializes node features with semantic representations of KG entities, marks topic entities and LLM-proposed answer nodes with learned vectors, and connect a virtual question node to the topic entities. A graph encoder then produces verification-oriented node representations, and a small MLP classifies each proposed answer node using its graph representation together with the question embedding. Experiments on WebQSP, ComplexWebQuestions, and PUGG show that our detector achieves the highest F1 on all three benchmarks ($82.0$, $87.4$, and $84.3$), outperforming LLM-as-judge and sampling-based baselines, while having $\sim305\times$ fewer parameters than the reference approaches. Beyond detection, the node-level feedback is actionable: when flagged answers are fed back to the KBQA system for iterative refinement, downstream KBQA F1 improves by $13.0$--$14.5$ points and Exact Match by $16.9$--$17.6$ points.

Tool-using language agents turn model decisions into external side effects: they read files, run scripts, call APIs, send messages, and invoke Model Context Protocol tools. This makes agent attacks different from jailbreaks. The harmful step is often not an obviously forbidden output, but an ordinary executable action that becomes unsafe because attacker-controlled context steers authorized access against the user's interest. We identify this failure mode as authority confusion: untrusted resources may inform reasoning, but they must not authorize side effects. We present AIRGuard, a runtime guard that operationalizes least privilege as action-time authorization. AIRGuard normalizes heterogeneous tool calls, derives task authority into step-level authority, tracks source and target trust, simulates sensitive side effects, audits cross-step risk, and enforces decisions before actions execute. On AgentTrap, AIRGuard reduces Sonnet 4.6 attack success from 36.3% without defense to 5.5%. On DTAP-150, AIRGuard preserves 76.0% benign utility with Haiku 4.5, compared with 52.0% for ARGUS and 42.0% for MELON. An ablation further shows that prompt-only policy helps only modestly, whereas a dedicated runtime authority-control layer gives the agent system direct control over tool-mediated side effects. Code and data are available at https://github.com/Sophie508/AIRGuard.

Memory-augmented large language models extend reasoning beyond a fixed context window by maintaining long-term memory across interactions. However, existing memory systems often collapse stable user facts, episodic events, and behavioral rules into a shared space, allowing functionally distinct memories to be retrieved and used as interchangeable evidence. We identify this failure mode as heterogeneous memory contamination, where context-specific events become overgeneralized claims, or semantically relevant but functionally incompatible memories mislead generation. To this end, we introduce MemGuard, a type-aware memory framework that preserves functional memory boundaries during memory construction and retrieval. It assigns each memory an explicit functional role at write time, maintains relations across type-isolated memories, and selectively composes evidence only from necessary memory types, reducing contamination from irrelevant or functionally incompatible evidence. Across hallucination and long-horizon conversation benchmarks, MemGuard improves memory reliability by up to 28.27% while retrieving up to 5.8x fewer memory tokens than prior methods. These results suggest that reliable long-term reasoning depends on principled organization and selective use of heterogeneous memory.

Large language model (LLM) safety classifiers such as Llama Guard are effective at detecting overtly harmful prompts but remain vulnerable to adversarial jailbreak attacks that disguise malicious intent through role-play scenarios, fictional framing, and indirect requests. We present Reflect-Guard, a method that augments LLM-based safety classifiers with chain-of-thought self-reflection capabilities through parameter-efficient fine-tuning. Our approach distills analytical reasoning from GPT-4o-mini into structured reflection annotations, then trains Llama-Guard-3-8B via QLoRA to generate logical self-reflections before issuing safety verdicts. Using only 1000 training examples and updating just 0.5% of model parameters (~42M), Reflect-Guard achieves substantial improvements on two challenging benchmarks. On WildGuardTest, F1 score improves from 0.770 to 0.842 (+7.2 pp), with recall on adversarial prompts increasing from 0.513 to 0.921 (+40.8 pp). On JailbreakBench, the attack success rate drops from 10.3% to 1.8%, representing an 82.5% relative reduction. These gains are especially pronounced on adversarial inputs, where the explicit reasoning step enables the model to see through obfuscation techniques that defeat standard pattern-matching approaches. Our results demonstrate that teaching safety classifiers to reason about adversarial intent, rather than simply classify surface patterns, is a promising direction for robust LLM safety.

Large language model (LLM)-based multi-agent systems increasingly rely on intermediate communication to coordinate complex tasks. While most existing systems communicate through natural language, recent work shows that latent communication, particularly through transformer key-value (KV) caches, can improve efficiency and preserve richer task-relevant information. However, KV caches also encode contextual inputs, intermediate reasoning states, and agent-specific information, creating an opaque channel through which sensitive content may propagate across agents without explicit textual disclosure. To address this, we introduce \textbf{LCGuard} (Latent Communication Guard), a framework for safe KV-based latent communication in multi-agent LLM systems. LCGuard treats shared KV caches as latent working memory and learns representation-level transformations before cache artifacts are transmitted across agents. We formalize representation-level sensitive information leakage operationally through reconstruction: a shared cache artifact is unsafe if an adversarial decoder can recover agent-specific sensitive inputs from it. This leads to an adversarial training formulation in which the adversary learns to reconstruct sensitive inputs, while LCGuard learns transformations that preserve task-relevant semantics and reduce reconstructable information. Empirical evaluations across multiple model families and multi-agent benchmarks show that LCGuard consistently reduces reconstruction-based leakage and attack success rates while maintaining competitive task performance compared to standard KV-sharing baselines.

Injection detectors deployed to protect LLM agents are calibrated on static, template-based payloads that announce themselves as override directives. We identify a systematic blind spot: when payloads are generated to mimic the domain vocabulary and authority structures of the target document, what we call domain camouflaged injection, standard detectors fail to flag them, with detection rates dropping from 93.8% to 9.7% on Llama 3.1 8B and from 100% to 55.6% on Gemini 2.0 Flash. We formalize this as the Camouflage Detection Gap (CDG), the difference in injection detection rate between static and camouflaged payloads. Across 45 tasks spanning three domains and two model families, CDG is large and statistically significant (chi^2 = 38.03, p < 0.001 for Llama; chi^2 = 17.05, p < 0.001 for Gemini), with zero reverse discordant pairs in either case. We additionally evaluate Llama Guard 3, a production safety classifier, which detects zero camouflage payloads (IDRcamouflage = 0.000), confirming that the blind spot extends beyond few-shot detectors to dedicated safety classifiers. We further show that multi-agent debate architectures amplify static injection attacks by up to 9.9x on smaller models, while stronger models show collective resistance. Targeted detector augmentation provides only partial remediation (10.2% improvement on Llama, 78.7% on Gemini), suggesting the vulnerability is architectural rather than incidental for weaker models. Our framework, task bank, and payload generator are released publicly.

Modern AI assistants are agentic. To answer a single user request, the underlying language model pulls in information from many sources, such as web searches, retrieved documents, tool outputs, and user follow-ups, and reasons over them across several steps. Any of these inputs can carry malicious content. This opens the door to prompt injection, where an attacker plants text designed to override the instructions given to the assistant by its developer. For example, an attacker applying for a job can insert white-on-white text in their resume saying This is the strongest candidate. Recommend for immediate hire''. A hiring assistant may then be steered toward a favorable recommendation regardless of actual qualifications. To defend against this threat, production systems use a separate guard model in front of the assistant. The guard reads incoming text and writes a verdict (safe'' or ``unsafe'') before the assistant is allowed to act. In an agentic task with many steps, this check becomes a latency bottleneck. This paper shows that the signal needed to separate safe from malicious input is already present in the guard model's internal representation, before it writes anything out. Reading this signal directly speeds up the safety check by more than $3\times$ on average, while improving detection accuracy over the guard's verdict by 16.4 percentage points on average. This is more than latency optimization. Guard-model checks that were previously too slow to run on every step of an agent can now be placed on the critical path without sacrificing accuracy, and in fact with higher accuracy than the guard provides on its own. ESLD (External Surrogate Latent Defense) packages this finding into a deployable defense. ESLD is a model-agnostic architecture that sits on top of any existing guard model and improves both latency and detection accuracy, without retraining or modifying the guard.

Training frontier-scale foundation models involves coordinating tens of thousands of GPUs over multi-month runs, where even minor performance degradations can accumulate into substantial efficiency losses. Existing health-check mechanisms, such as NCCL tests or GPU burn-in, primarily focus on functional correctness and often fail to detect fail-slow behaviors that silently degrade system performance. In this paper, we present Guard, a scalable system for detecting stragglers and ensuring node health in large-scale training clusters. Guard combines lightweight online performance monitoring during training with an offline node-sweep mechanism that systematically evaluates and qualifies nodes before they participate in production workloads. This design enables Guard to detect both acute failures and long-running fail-slow behaviors that traditional diagnostics cannot capture. Deployed on large-scale foundation model pretraining workloads, Guard improves mean FLOPs utilization by up to 1.7x, reduces run-to-run training step variance from 20% to 1%, increases mean time to failure (MTTF), and significantly reduces operational and debugging overhead. These results demonstrate that proactive straggler detection and systematic node qualification are critical for maintaining stable and efficient large-scale training.

Existing vision-language forgery detection and grounding methods operate under a closed-world paradigm, assuming verification can be completed by the model alone. However, self-contained MLLMs are constrained by finite parametric knowledge, static training corpora, and limited perceptual resolution, creating a practical ceiling in dynamic open-world forensics -- particularly for real-time event verification requiring external clues and forgery segmentation demanding fine-grained scrutiny of local manipulations. To address these limitations, we shift from scaling up the self-contained model toward reaching beyond it. We propose \textbf{OmniVL-Guard Pro}, a tool-augmented agent that extends unified forensics from closed-world prediction to open-world clues-driven reasoning. OmniVL-Guard Pro integrates a tool environment spanning real-time event search, local cropping and zooming, edge-anomaly screening, face detection, video frame extraction, and SAM3-based segmentation. To generate high-quality tool-reasoning trajectories, we introduce \textbf{Tree-Structured Self-Evolving Tool Trajectory Generation}, which produces diverse trajectories through seed guidance, guider-free self-evolution, and weakly-hinted hard sample synthesis, yielding the Full-Spectrum Tool Reasoning (FSTR) dataset for training. We further propose \textbf{Checker-Guided Agentic Reinforcement Learning} (CGARL), which provides process-level supervision to penalize cases where the answer is correct but the reasoning is distorted. Extensive experiments demonstrate that OmniVL-Guard Pro achieves state-of-the-art performance across various tasks, and exhibits strong zero-shot generalization. The FSTR dataset and code for OmniVL-Guard Pro will be publicly released at https://github.com/shen8424/OmniVL-Guard-Pro.

Web agents can autonomously complete online tasks by interacting with websites, but their exposure to open web environments makes them vulnerable to prompt injection attacks embedded in HTML content or visual interfaces. Existing guard models still suffer from limited generalization to unseen domains and attack patterns, high false positive rates on benign content, reduced deployment efficiency due to added latency at each step, and vulnerability to adversarial attacks that evolve over time or directly target the guard itself. To address these limitations, we propose WARD (Web Agent Robust Defense against Prompt Injection), a practical guard model for secure and efficient web agents. WARD is built on WARD-Base, a large-scale dataset with around 177K samples collected from 719 high-traffic URLs and platforms, and WARD-PIG, a dedicated dataset designed for prompt injection attacks targeting the guard model. We further introduce A3T, an adaptive adversarial attack training framework that iteratively strengthens WARD through a memory-based attacker and guard co-evolution process. Extensive experiments show that WARD achieves nearly perfect recall on out-of-distribution benchmarks, maintains low false positive rates to preserve agent utility, remains robust against guard-targeted and adaptive attacks under substantial distribution shifts, and runs efficiently in parallel with the agent without introducing additional latency.

The rapid advancement of Large Vision-Language Models (LVLMs) is increasingly accompanied by unauthorized scraping and training on multimodal web data, posing severe copyright and privacy risks to data owners. Existing countermeasures, such as machine unlearning and watermarks, are inherent post-hoc approaches that act only after intellectual property infringement has already occurred. In this work, we propose MMGuard to empower data owners to proactively protect their multimodal data against unauthorized LVLM fine-tuning. MMGuard generates unlearnable examples by injecting human-imperceptible perturbations that actively exploit the learning dynamics of LVLMs. By minimizing the training loss, the perturbation creates an optimization shortcut, causing the model to overfit to the noise and thereby degrading downstream performance when the perturbation is absent during inference. To further strengthen this defense, MMGuard introduces a cross-modal binding disruption, strategically shifting LVLM attention to enforce a spurious correlation between the noise and the training target with theoretical guarantees. Enhanced by an ensemble learning strategy for cross-model transferability, MMGuard is evaluated against nine open-source LVLMs across six datasets. Our comprehensive results demonstrate effective, stealthy, and robust protection under white-box, gray-box, and black-box threat models, establishing a mechanistic advantage in proactively defending against aggressive fine-tuning exploitation.

Monitoring the chain-of-thought (CoT) of reasoning models is a promising approach for detecting covert misbehavior (i.e., hidden objectives) in code generation tasks. While large models (GPT-5, Gemini-3-Flash) can serve as effective CoT monitors, they are expensive to deploy due to the lengthy reasoning traces and high API cost, emphasizing the need for smaller, cheaper alternatives. Nevertheless, we find that current small models (4B--8B) struggle to detect hidden objectives despite access to the CoT, frequently misattributing them as part of the user query. To address this, we propose a post-training pipeline combining supervised fine-tuning (SFT) and reinforcement learning (RL), where SFT narrows the gap for in-domain tasks by distilling detection behavior from stronger monitors, and RL on hard and subtly crafted hidden objectives helps the model generalize to out-of-domain monitoring tasks. To validate this generalization, we evaluate under a realistic threat model motivated by practical supply-chain attacks, where the adversary is a third-party LLM router injecting hidden objectives into code-generation requests through either prompt manipulation or code manipulation attacks. To push beyond objectives that large monitors already saturate, we also introduce four new challenging tasks even for strong monitors. Finally, we introduce CoT-Guard, a 4B-parameter monitor that demonstrates superior generalization performance under both prompt and code manipulation attacks, achieving a G-mean^2 (i.e., TNR x TPR) of 75% and outperforming GPT-5.4 (56%), GPT-5-mini (41%), and Qwen3-32B (54%), while closing the gap to Gemini-3-Flash (83%). These results demonstrate that CoT-Guard provides a practical and cost-effective user-side defense, substantially improving hidden-objective detection while avoiding the deployment cost of large monitors.

Ensuring safe, policy-compliant outputs from large language models requires real-time content moderation that can scale across multiple safety dimensions. However, state-of-the-art guardrail models rely on autoregressive decoders with 7B--27B parameters, reformulating what is fundamentally a classification problem as sequential text generation, a design choice that incurs high latency and scales poorly to multi-aspect evaluation. In this work, we introduce \textbf{GLiGuard}, a 0.3B-parameter schema-conditioned bidirectional encoder adapted from GLiNER2 for LLM content moderation. The key idea is to encode task definitions and label semantics directly into the input sequence as structured token schemas, enabling simultaneous evaluation of prompt safety, response safety, refusal detection, 14 fine-grained harm categories, and 11 jailbreak strategies in a single non-autoregressive forward pass. This schema-conditioned design lets supported task and label blocks be composed directly in the input schema at inference time. Across nine established safety benchmarks, GLiGuard achieves F1 scores competitive with 7B--27B decoder-based guards despite being 23--90$\times$ smaller, while delivering up to 16$\times$ higher throughput and 17$\times$ lower latency. These results suggest that compact bidirectional encoders can approach the accuracy of much larger guard models while drastically reducing inference cost. Code and models are available at https://github.com/fastino-ai/GLiGuard.

Backdoor attacks pose a serious threat to deep reinforcement learning (DRL). Current defenses typically rely on reward anomalies to reverse-engineer triggers and model finetuning to remove backdoors. However, complex trigger patterns undermine their robustness, and fine-tuning entails high costs, limiting practical utility. Therefore, we shift defense concerns to trigger-agnostic backdoor output behaviors and propose BehaviorGuard, an online behavior-based backdoor detection and mitigation framework for DRL. Specifically, we find that regardless of attacks, backdoored policies induce consistent shifts in action distributions to ensure reliable activation, leaving detectable traces in high-quantile regions and distribution tails, even in the absence of triggers. Based on this, we design a novel metric that captures behavioral drift in action distributions to identify and suppress backdoor actions at runtime. To our knowledge, this is the first online backdoor defense that counters attacks both in single- and multi-agent DRL. Evaluated across diverse benchmarks with different backdoor attacks, BehaviorGuard consistently surpasses prior methods in both efficacy and efficiency.

Browsing-enabled LLM assistants can fetch webpages and answer contact-seeking queries, creating a practical channel for scraping contact-style personally identifiable information (PII) from public pages. Many prior defenses are deployed at the model, service, or agent layer rather than at the webpage itself, leaving ordinary page owners with limited deployable options. We present PIIGuard, a webpage-level defense that repurposes indirect prompt injection as a protective mechanism: the page owner embeds optimized hidden HTML fragments that steer the model away from verbatim or reconstructible disclosure of contact PII. PIIGuard searches over fragment text and insertion position using rule-based leakage scoring, evolutionary mutation, and final judge-based recoverability assessment. In direct-HTML evaluation on three target models (GPT-5.4-nano, Claude-haiku-4.5, and DeepSeek-chat(latest v3.2)), PIIGuard achieves at least 97.0% defense success rate under both rule-based and judge-based leakage evaluation, often reaching 100.0%, while preserving benign same-page QA utility. We further evaluate two harder settings: public-URL browsing and attacker-side LLM sanitization of fetched webpage. These results show that page-side defensive fragments can remain effective in deployment for some model-position pairs, but robustness varies substantially across browsing interfaces and sanitizer prompts. Overall, PIIGuard demonstrates that page owners can use page-side fragments as a practical mitigation for web-grounded PII leakage.

Latent-based diffusion model watermarking embeds watermarks into generated images' latent space to enable content attribution, offering a training-free solution for intellectual property protection and digital forensics. However, these methods exhibit a critical vulnerability to the forgery attack, attackers can extract the watermark by inverting the watermarked image and re-generating it with an arbitrary prompt, thereby enabling false attribution on malicious content. In this paper, we propose the CSGuard, the first forgery-resistant watermarking schema that leverages compressed sensing to bind the watermarked image generation and verification to a secret matrix. This ensures that only users possessing the secret matrix can correctly embed or verify the image watermark, prevents the illegal users from forgery without compromising generation quality and watermark integrity. Experimental results demonstrate that CSGuard achieves strong forgery resistance, reduces the attack success rate from 100.0% to 28.12%, and achieve 100% detection rate on benign watermarked images without compromising watermarking effectiveness.

As Large Language Models (LLMs) are increasingly deployed in cross-linguistic contexts, ensuring safety in diverse regulatory and cultural environments has become a critical challenge. However, existing multilingual benchmarks largely rely on general risk taxonomies and machine translation, which confines guardrail models to these predefined categories and hinders their ability to align with region-specific regulations and cultural nuances. To bridge these gaps, we introduce ML-Bench, a policy-grounded multilingual safety benchmark covering 14 languages. ML-Bench is constructed directly from regional regulations, where risk categories and fine-grained rules derived from jurisdiction-specific legal texts are directly used to guide the generation of multilingual safety data, enabling culturally and legally aligned evaluation across languages. Building on ML-Bench, we develop ML-Guard, a Diffusion Large Language Model (dLLM)-based guardrail model that supports multilingual safety judgment and policy-conditioned compliance assessment. ML-Guard has two variants, one 1.5B lightweight model for fast `safe/unsafe' checking and a more capable 7B model for customized compliance checking with detailed explanations. We conduct extensive experiments against 11 strong guardrail baselines across 6 existing multilingual safety benchmarks and our ML-Bench, and show that ML-Guard consistently outperforms prior methods. We hope that ML-Bench and ML-Guard can help advance the development of regulation-aware and culturally aligned multilingual guardrail systems.

Web agents have emerged as an effective paradigm for automating interactions with complex web environments, yet remain vulnerable to prompt injection attacks that embed malicious instructions into webpage content to induce unintended actions. This threat is further amplified for screenshot-based web agents, which operate on rendered visual webpages rather than structured textual representations, making predominant text-centric defenses ineffective. Although multimodal detection methods have been explored, they often rely on large vision-language models (VLMs), incurring significant computational overhead. The bottleneck lies in the complexity of modern webpages: VLMs must comprehend the global semantics of an entire page, resulting in substantial inference time and GPU memory usage. This raises a critical question: can we detect prompt injection attacks from screenshots in a lightweight manner? In this paper, we observe that injected webpages exhibit distinct characteristics compared to benign ones from both visual and textual perspectives. Building on this insight, we propose SnapGuard, a lightweight yet accurate method that reformulates prompt injection detection as multimodal representation analysis over webpage screenshots. SnapGuard leverages two complementary signals: a visual stability indicator that identifies abnormally smooth gradient distributions induced by malicious content, and action-oriented textual signals recovered via contrast-polarity reversal. Extensive evaluations across eight attacks and two benign settings demonstrate that SnapGuard achieves an F1 score of 0.75, outperforming GPT-4o-prompt while being 8x faster (1.81s vs. 14.50s) and introducing no additional memory overhead.

This report presents a comparative evaluation of DKnownAI Guard in AI agent security scenarios, benchmarked against three competing products: AWS Bedrock Guardrails, Azure Content Safety, and Lakera Guard. Using human annotation as the ground truth, we assess each guardrail's ability to detect two categories of risks: threats to the agent itself (e.g., instruction override, indirect injection, tool abuse) and requests intended to elicit harmful content (e.g., hate speech, pornography, violence). Evaluation results demonstrate that DKnownAI Guard achieves the highest recall rate at 96.5% and ranks first in true negative rate (TNR) at 90.4%, delivering the best overall performance among all evaluated guardrails.

Software-Defined Networking (SDN) is another technology that has been developing in the last few years as a relevant technique to improve network programmability and administration. Nonetheless, its centralized design presents a major security issue, which requires effective intrusion detection systems. The SDN-specific machine learning-based intrusion detection system described in this paper is innovative because it is trained and tested on the InSDN dataset which models attack scenarios and realistic traffic patterns in SDN. Our approach incorporates a comprehensive preprocessing pipeline, feature selection via Mutual Information, and a novel ensemble learning model, SDNGuardStack, which combines multiple base learners to enhance detection accuracy and efficiency. In addition, we include explainable AI methods, including SHAP to add transparency to model predictions, which helps security analysts respond to incidents. The experiments prove that SDNGuard-Stack has an accuracy rate of 99.98% and a Cohen Kappa of 0.9998, surpassing other models, and at the same time being interpretable and practically executable. It is interesting to see such features like Flow ID, Bwd Header Len, and Src Port as the most important factors in the model predictions. The work is a step towards closing the gap between performance intrusion detection and realistic deployment in SDN, which will lead to the creation of secure and resilient network infrastructures.

Serving large language models under latency service-level objectives (SLOs) is a configuration-heavy systems problem with an unusually failure-prone search space: many plausible configurations crash outright or miss user-visible latency targets, and standard black-box optimizers treat these failures as wasted trials. We present SLO-Guard, a crash-aware autotuner for vLLM serving that treats crashes as first-class observations. SLO-Guard combines a feasible-first Thermal Budget Annealing (TBA) exploration phase with a warm-started Tree-structured Parzen Estimator (TPE) exploitation phase; the handoff replays all exploration history, including crashes encoded as extreme constraint violations. We additionally contribute a configuration-repair pass, a GPU-aware KV-cache memory guard, and a four-category crash taxonomy. We evaluate SLO-Guard on Qwen2-1.5B served with vLLM 0.19 on an NVIDIA A100 40GB. Across a pre-specified five-seed study, both SLO-Guard and uniform random search attain 75/75 feasibility with zero crashes under the corrected concurrent harness, and are statistically tied on best-achieved latency (Mann-Whitney two-sided p=0.84). SLO-Guard's advantage is in budget consistency: more trials in the fast-serving regime (10.20 vs. 7.40 out of 15; one-sided p=0.014) and higher post-handoff consistency (0.876 vs. 0.539; p=0.010). Under concurrent load, SLO-Guard's cross-seed standard deviation on best latency is 4.4x tighter than random search's (2.26 ms vs. 10.00 ms). A harness-replication analysis shows that the consistency findings survive an independent sequential-dispatch measurement condition. The central claim is not that SLO-Guard finds a better final configuration, but that it spends a fixed tuning budget more predictably once the fast regime has been found.