Hijacking

When an indirect prompt injection succeeds against an LLM agent, the compromise is visible in the agent's own behavior: a benign prefix of tool calls, a poisoned observation, and a suffix of actions that serve the attacker. An operator needs three facts: where the attack entered, which steps it corrupted, and whether apparent poison was resisted. Existing systems return either a whole-trace verdict or a single unsafe index. We present DriftNet, a dual-head trajectory Transformer that reads a logged tool-call trajectory and answers all three questions in one forward pass: one head classifies the trajectory as compromised or not, and a second assigns every step one of four labels (benign, injection point, hijacked, failed injection). To our knowledge it is the first supervised detector to produce this joint output. A frozen sentence encoder and four identity-free world features embed each step; the trained trunk, under two million parameters and optimized with a class-weighted joint objective over both heads, needs no access to the agent's model. On the task-disjoint split of the AgentDrift benchmark (12,536 trajectories, 71,024 labeled steps), with a 20-configuration sweep bounding hyperparameter sensitivity to 0.011 F1 and the test part evaluated exactly once, DriftNet reaches trajectory-level F1 of 0.983, exact injection-point recovery on 98.7% of attacked trajectories, hijacked-span IoU of 0.979, zero flags on 218 resisted attacks, and 2.9% flags on hard negatives. A surface baseline retrained on the identical split recovers 11.1% of partial hijacks and 17.1% of delayed executions; DriftNet reaches 98.6% and 93.2% while lowering every false-alarm rate. Reading all 26 residual errors shows that most misses trace to trajectories whose labeled injection observation carries no legible instruction, and we report the benchmark's measured world-identity regularity alongside the results.

This paper presents an end-to-end evaluation framework for image-triggered command injection against computer-use agents (CUAs). The goal is to test whether a local visual patch can induce verifiable environmental consequences along the full chain of screenshot input, VLM generation, action parsing, and environment execution. We train and deploy patches on author-controlled GitHub Pages pages and a locally deployed CSDN clone, and evaluate them in real environments across five open-source or publicly available GUI-agent or vision-language-model (VLM) backends. Our experiment aggregates 600 instance-level online cases, with T-ASR, TAPR, and E2E-ASR reaching 84.5%, 47.0%, and 20.3%, respectively. Trajectory analysis further shows that in some successful cases the agent first executes a malicious terminal command and then continues the original benign task. These results indicate that optimized local visual signals can affect not only VLM outputs but also propagate through the execution pipeline of open CUAs and create real environmental risk.

Security evaluations of tool-using agents often equate stored labels with behavioral facts. We audit a preserved campaign by tracing 10,200 execution rows to 180 model-bound requests, 45 semantic requests, and 15 observable stimuli. Two schema treatments were delivered, but the planned external payload-family corpus was not. The historical grader exhibited direct treatment leakage: treatment metadata gated the ATTACK_SUCCESS class, so fixed behavior could change class under treatment relabeling. A treatment-blind reconstruction corrects 58 historical ATTACK_SUCCESS or HIJACK_ATTEMPT labels to authorized benign completions while preserving three verified protected-data transfers and one separate unauthorized-forwarding case. The locked v2 census contains exactly zero ATTACK_SUCCESS records, while the forwarding case remains a HIJACK_ATTEMPT at a semantic boundary concerning objective completion. A dual-reviewer blinded concordance review of all 96 requests deemed structurally interpretable by locked v2 produced identical reviewer-consensus classes but differed from the locked codebook on four construct-boundary cases. We contribute a seven-link Integrity Chain and an executable, scope-bounded endpoint-integrity linter. The result is a campaign-bounded measurement audit, not a population attack-rate, model-ranking, defense-efficacy, or causal estimate.

LLM agents increasingly rely on third-party skills, using natural-language descriptions for selection and instruction bodies for planning. This progressive-disclosure design exposes two sequential control points to untrusted publishers: a static skill may steer an otherwise correct task onto an unnecessarily costly trajectory. Prior work studies selection manipulation, malicious skill instructions, and tool-chain resource amplification largely separately, leaving their end-to-end composition unclear. We introduce Convergent Detour Hijacking (CDH), a text-only, runtime-independent attack that couples these stages. Under shared semantic cover, a description establishes relevance during selection, while an aligned body reuses that rationale to fabricate plausible dependencies during planning. CDH attracts an attacker-controlled coordinator alongside legitimate skills, recruits unnecessary benign skills into a bounded detour, and then re-enters the original route to preserve task completion. We evaluate it across multiple LLM backends and 491 held-out tasks under single-task and multi-turn conditions. On DeepSeek-V4-Pro, the matched coordinator is selected in 80.02% of tasks; among coordinator-hit runs that complete tasks, token consumption and end-to-end execution time increase by 66.91% and 92.45%, respectively, while aggregate task completion remains comparable. Thus, correct outcomes do not guarantee trajectory integrity or cost safety.

Many single-cell annotation tools refine an initial cell label using nearby cells or cluster-level voting. We study whether this refinement can be manipulated without changing the target cell. We introduce CohortHijack, a robustness audit that removes selected non-target cells from the query cohort while preserving the target expression profile, base prediction, and trained model. We evaluate random and structured removal methods, together with greedy, multi-start, and beam search, on PBMC3K and Paul15 using logistic regression and calibrated linear SVM classifiers. Structured removal was consistently stronger than random removal on Paul15. Multi-start search changed 24.33% of linear-SVM targets and 19.67% of logistic-regression targets while removing a small fraction of the cohort and keeping mean collateral changes below 0.4%. Ablations confirmed that the effect disappeared when neighborhood refinement was disabled. We also evaluated CellTypist majority voting, where independent predictions remained unchanged across all evaluations, but refined labels changed after small companion-cell removals. These findings identify query cohort composition as a target-preserving attack surface in single-cell annotation.

Large Language Models (LLMs) have been widely applied in high-stakes decision-making scenarios such as corporate strategy, and users are increasingly relying on their outputs. However, the deep integration of open-source model sharing ecosystems with LLM-powered critical decision-making applications also introduces critical risks: if an attacker can manipulate the model's cognitive stance, they can indirectly influence the judgments and actions of downstream decision-makers. This paper defines such threats as decision-level hijacking. Existing attacks fail to achieve targeted cognitive manipulation without triggering prohibited content or degrading model functionality. To fill this gap, this paper reveals that Bit-Flip Attacks (BFAs) can serve as an attack vector for inducing decision-level hijacking, requiring no real-time interaction or control over the training process, and only a minimal number of weight bits need to be flipped after deployment to achieve stealthy, low-cost, and persistent cognitive manipulation. Therefore, we propose CogBias, a cognitive bias injection framework for LLMs. CogBias converts subjective preferences into optimization signals via a differentiable sentiment evaluator, uses a multi-objective loss to jointly constrain multiple dimensions, and constructs BitScout to locate critical bits, achieving targeted cognitive intervention under an ultra-sparse flip budget. Experiments on Llama-3.2-3B, Mistral-7B, and Qwen2.5-14B, as well as on the commercial recommendation and controversial factual topic scenarios, demonstrate that flipping only a small number of bits stably induces significant stance shifts on target topics, while the impact on non-target tasks and overall output distribution is limited. This work demonstrates that minute perturbations to low-level weight data suffice to undermine the high-level value alignment of LLMs.

Key-Value (KV) cache reduces inference latency in large language models (LLMs). Traditional prefix-based reuse has low cache hit rates across inference requests because it requires exact token and position matches. To improve efficiency, recent system optimizations introduce position-independent KV reuse, allowing KV cache to be reused whenever identical text chunks appear, regardless of their position in the sequence. We show this design introduces a new threat, KV Cache Hijacking. Since KV caches are retrieved by token match but encode the context in which they were originally computed, the KV tied to a benign-looking token chunk may encode an attacker-controlled prefix. When later reused in a victim query, this contaminated KV silently hijacks the model's behavior, even if no attacker-controlled text appears in the input. We introduce HIJACKKV, the first attack framework that systematically exploits this vulnerability, demonstrating its severity and practicality. HIJACKKV optimizes an attacker-controlled prefix, so that the KV computed for a subsequent common benign text encodes the attacker's goal, while the text remains unchanged for future cache hits. HIJACKKV achieves an average 94% success rate in a single attempt, remains effective under realistic constraints including low hit rates (10%) and frequent recomputation (50%), persists over multi-turn interactions, and transfers across models in black-box settings. We further provide design insights for building secure KV reuse systems.

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.

Large language model (LLM) agents are rapidly moving from conversational interfaces to software components that plan, invoke tools, maintain memory, and act on external environments. This transition changes the nature of security risk. In agentic settings, failures are no longer limited to unsafe text generation. Untrusted content may redirect control flow, misuse tool privileges, corrupt persistent state, leak sensitive information, or trigger harmful external actions. At the same time, research on LLM agent security is expanding quickly but remains fragmented across attack families, defense layers, application domains, and evaluation settings. This paper synthesizes 247 papers through a lifecycle-based, systems-oriented framework that models agent security around the interaction of information flow, delegated authority, and persistent state. We organize the literature around four questions: how LLM agent security should be modeled, which threat surfaces and attack families dominate, what defenses have been proposed and with what tradeoffs, and how security claims are evaluated. We find that prompt injection and tool-mediated control-flow hijacking still dominate the field, while persistent state corruption and multi-agent propagation are becoming central emerging concerns. We further find that current defenses provide useful building blocks but remain weakly compositional, and that existing benchmarks still underrepresent long-horizon, stateful, and deployment-sensitive risks. We argue that secure LLM agents require explicit trust boundaries, principled privilege control, provenance-aware state management, and evaluation practices aligned with realistic operational settings.

Large language model (LLM) agents increasingly leverage long term memory to support persistent and autonomous task execution. However, this capability also introduces a new attack surface: memory poisoning, where adversaries can inject malicious information to influence future behavior. Existing memory poisoning attacks often assume that injected content can be stored directly in memory, overlooking the selective extraction and rewriting stages in modern memory pipelines. This makes prior methods ineffective under realistic settings. In this paper, we propose MemPoison, a novel memory poisoning attack that bypasses selective memory mechanisms in LLM agents, where an attacker can inject triggerable backdoors into the agent's long-term memory through dialogue interactions, thereby misleading its subsequent responses. MemPoison introduces three key components: (i) a semantic relational bridge that binds the trigger and payload into a coherent statement to ensure they are extracted into memory together; (ii) entity masquerading that optimizes triggers to mimic named entities, resisting rewriting; and (iii) joint embedding optimization that shapes trigger-injected texts into a tight cluster in the embedding space while maintaining isolation from benign embeddings for stealth. Evaluations across different agent domains and memory mechanisms show MemPoison achieves attack success rates up to 0.95, outperforming existing baselines. Mechanistic analysis indicates that the attack exploits embedding-space anisotropy and shifts attention patterns, highlighting core vulnerabilities in selective memory systems. We evaluate multiple defense strategies and demonstrate their fundamental limitations in mitigating the attack.

Cryptographic watermarking is a leading defense for attributing text generated by large language models (LLMs). Existing schemes, including KGW, Unigram, and DipMark, derive their security guarantees from the assumption that the underlying pseudo-random number generator (PRNG) is trustworthy. This work introduces SeedHijack, the first supply-chain attack on LLM watermarking that is simultaneously (i) blind -- requiring no knowledge of the watermark key, detector, or model logits, (ii) integrity-preserving -- amplifying rather than erasing the watermark signal, and (iii) orthogonal to detection -- the attack-induced bias is statistically independent of all content-side detector statistics, ensuring that amplification and evasion coexist without trade-off. Rather than perturbing generated text, SeedHijack replaces the PRNG at the supply-chain layer, biasing green-list selection without altering output tokens or degrading text quality. Across three watermarking schemes and three open-source LLMs, the attack triggers 0/6 state-of-the-art content-side statistical detectors while inflating the watermark z-score up to 2.42x (system-level defenses such as entropy-source attestation remain orthogonal and complementary). A quantum random number generator (QRNG) countermeasure is shown to fully neutralize the attack while preserving benign watermarking utility. These findings establish PRNG integrity as a first-class security requirement for cryptographic content-provenance systems.

While Vision-Language-Action (VLA) models have emerged as powerful generalist policies, their severe vulnerability to adversarial patches significantly hinders their deployment in safety-critical domains. Moreover, existing patch attacks primarily focus on white-box settings, heavily overfitting to the specific action output space of the target model, which results in poor cross-architecture transferability. To overcome this limitation, we propose VLA-Hijack, a unified adversarial framework that breaks the transferability bottleneck by exploiting a fundamental vulnerability identified in this work: before planning any motion, a VLA model must first use visual information to locate its own robotic arm within the environment. Targeting this shared visual self-localization process, our approach concurrently optimizes Attention-Guided Proprioceptive Suppression to inhibit the real robotic arm's features, and Multimodal Proprioceptive Injection to establish the patch as a surrogate "phantom embodiment". By alternating between semantic concept anchoring and visual prototype projection, VLA-Hijack effectively severs the semantic relationship between the agent's true embodiment and its control policy. Extensive experiments across diverse architectures (OpenVLA, UniVLA, and CronusVLA) demonstrate that VLA-Hijack achieves superior optimization efficiency in white-box settings and sets a new SOTA for cross-architecture and cross-domain black-box transferability.

Retrieval-Augmented Generation (RAG) mitigates LLM hallucinations but introduces a critical vulnerability: corpus integrity. We present SilentRetrieval, a two-stage data poisoning attack that hijacks RAG systems through adversarially crafted yet fluent documents. Stage 1 uses Coordinated Beam Search, a multi-token joint optimization method with a fluency-similarity objective, to keep a poisoned host document retrievable while constraining perplexity. Stage 2 uses Context-Adaptive Trigger Generation, a lightweight trigger-fusion step driven by a frozen LLM, to integrate manipulation triggers into document content. Under a one-poisoned-document-per-query evaluation with synthetic target answers, SilentRetrieval achieves 84.6%/81.3% HR@10 and 57.5%/54.8% ASR-LLM on Natural Questions and MS MARCO, while maintaining near-benign perplexity. Cross-model evaluation across four target LLMs shows nontrivial effectiveness under a fixed trigger generator, and transfer tests against unseen retrievers, including ColBERT and commercial embedding models, yield 64.7% average HR@10 under the same injected-corpus protocol. In a sampled Wikipedia-scale evaluation, SilentRetrieval retains 74.2% HR@10 at a 0.016% poisoning ratio. Combined retrieval-side and generation-side defenses reduce attack success substantially but incur a latency trade-off. Human evaluation shows substantially lower flag rates than disfluent baselines, while remaining numerically more suspicious than benign content at the current sample size.

Autonomous computer use agents that powered by multimodal large language models (MLLMs) are emerging as capable assistants for completing complex digital workflows. However, real-world execution environments are far from ideal: pop-ups, resolution changes, and competing applications frequently interfere with agent perception and control. We introduce AgentHijack, a benchmark designed to evaluate the robustness of computer-use agents under common corruptions, where the uncertainties in dynamic environment disrupt the execution flow without direct adversarial intent. Specifically, AgentHijack introduces 9 configurable common corruptions to replicate realistic imperfect scenarios. We evaluate a variety of desktop tasks that utilize MLLM-based agents and discover that even minor instances of corruption can result in substantial performance degradation, which emphasizes the fragility of agents and underscores the necessity of robustness evaluation. Afterward, we propose AgentHijack-Agent, a framework that integrates an action generator with enhanced grounding capabilities and an onlooker responsible for behavior summarization and environment checking. Extensive experiments validate its effectiveness. Our code, environment, baseline models and data are publicly available at: https://AgentHijack.github.io.

LLM-based agents are increasingly deployed for complex tasks requiring planning, tool use, and interaction with external services. Their reliance on untrusted external content exposes them to indirect prompt injection (IPI), in which adversarial instructions embedded in retrieved data hijack agent behavior. Existing attacks rely on static payloads that cannot adapt to agent-specific defenses; even recent adaptive methods lack structured feedback to guide optimization. We introduce \oursys, a feedback-guided iterative framework that closes the loop between injection, diagnosis, and refinement: a rule-based diagnoser produces structured outcome labels with behavioral descriptions, and an LLM-based optimizer refines payloads conditioned on the full optimization history. A synthesis step generates new disguise seeds from failure patterns, enabling the strategy space to self-evolve. On AgentDojo and InjectAgent, \oursys substantially outperforms static baselines and existing adaptive methods across four victim models. Extension experiments on Claude Code, a production-grade coding agent with layered defenses, show that optimized payloads achieve full success on 5 of 9 targets; even those that resist full exploitation exhibit measurable improvement from iterative refinement. We further present a mechanistic analysis of IPI, identifying an attention-mediated threshold mechanism in mid-to-late layers; three causal interventions validate this finding and point to concrete defense directions.

Large language models (LLMs) are increasingly used as analyst assistants in security operations centers (SOCs), where they ingest log and alert data to produce triage labels, incident summaries, or remediation advice. We study a structural failure mode of this design: many log fields are attacker controlled. User agents, URLs, payloads, DNS queries, and attempted usernames can therefore carry instructions to the model alongside evidence of the intrusion. We call this setting \emph{log-substrate prompt injection}. We introduce a four-class taxonomy of log-substrate attacks: direct override (S1), persona hijack (S2), context manipulation (S3), and obfuscated payloads (S4). We evaluate 48 strategy-defense-task combinations using \texttt{gpt-4o-mini} as the analyst. Three findings stand out. First, direct overrides are ineffective in our setting: all S1 classification attacks achieve 0% suppression. In contrast, persona hijacks suppress 68% of malicious logs under a naive classifier and remain effective under stronger defenses. Second, summarization is the highest-risk task: context manipulation reaches 96% injection success without defenses and 38% even with constrained output. Third, defenses reduce but do not eliminate the attack surface: average injection success falls from 26.6% under naive prompting to 11.8% under our strongest defense. We also compare empirical results to a deterministic mock analyst and find that simulation substantially mispredicts current model behavior, especially for direct overrides. These results suggest that SOC copilots should treat raw log content as adversarial input rather than ordinary analyst context.

Multi-agent systems extend large language models (LLMs) by decomposing tasks among specialized agents, but their distributed decision process creates new attack surfaces. We identify semantic hijacking, an attack in which harmful requests are concealed within domain-specific narratives and propagated to a Manager through Worker reports, without any syntactic injection primitives. Across 42,000 adversarial trials over 12 Manager models and 7 Worker configurations, we uncover a capability paradox: as Worker capability increases, the mean system-level Attack Success Rate (ASR) increases from 18.4% to 63.9%, peaking at 94.4%. To explain this effect, we conduct multi-level mediation analysis on two independent datasets (47,807 interactions). This analysis shows that this paradox is driven by linguistic certainty: stronger Workers are more likely to interpret adversarial narratives as legitimate, convey their conclusions assertively, and thereby lead Managers to treat such confident endorsements as justification to execute. In our larger Worker-Only setting ($n_W$=14), certainty mediates 74% of the effect, with 95% confidence intervals (CI) excluding zero under both Monte Carlo and cluster bootstrap; the smaller Full-MAS setting ($n_W$ =6) shows a directionally consistent indirect effect. Worker-side safety prompting does not reliably mitigate this failure. Building on the mediation finding, we propose heterogeneous ensemble verification, which pairs Workers of asymmetric domain competence so their complementary vulnerabilities break the certainty-to-execution chain, reducing ASR from 52.8% to 2.0% with negligible benign-task impact. Our results show that upgrading components to stronger models can actively degrade system security, and that effective defenses require exploiting--rather than eliminating--capability asymmetries between agents.

Existing adversarial attacks on vision-language models (VLMs) can steer model outputs toward attacker-specified target responses, but their effectiveness often degrades when the same perturbed input is paired with different textual queries. This paper studies cross-query response manipulation, where a single adversarial example is expected to remain effective across diverse user queries. We first analyze the limitations of existing attacks and find that successful transfer is closely associated with preserving an image-dominant attention pattern during response generation. Motivated by the observation, we propose \textbf{Attention Hijacking}, a novel adversarial attack that explicitly steers internal attention distributions toward a persistent image-dominant pattern. By amplifying the influence of visual tokens on target response tokens while suppressing the competing influence of textual tokens, our method reduces the dependence of the manipulated output on the specific wording of the query. Extensive experiments on widely used VLMs show that Attention Hijacking substantially improves cross-query transferability across diverse target responses and unseen queries. The method also extends effectively to multiple attack scenarios, offering new insights into the role of attention stability in transferable response manipulation for VLMs.

Automation platforms such as GitHub Actions and n8n are increasingly adopting so-called agentic workflows, which integrate Large Language Model (LLM) agents for tasks such as code review and data synchronization. While bringing convenience for developers, this integration exposes a new risk: An adversary may control and craft certain inputs, such as GitHub issue comments, to manipulate the LLM agent for unwanted actions, such as credential exfiltration and arbitrary command execution. To our knowledge, no prior academic work has studied such a risk in agentic workflows. In this paper, we design the first detection and exploitation framework, called JAW, to hijack agentic workflows hosted on automation platforms via a novel approach called Context-Grounded Evolution. Our key idea is to evolve agentic workflow inputs under the contexts derived from hybrid program analysis for hijacking purposes. Specifically, JAW generates agentic workflow contexts through three analyses: (i) static path-feasibility analysis to identify feasible agent-invocation paths and the input constraints required to trigger them, (ii) dynamic prompt-provenance analysis to determine how that input is transformed and embedded into the LLM context, and (iii) capability analysis to identify the actions and restrictions available to the agent at runtime. Our evaluation of JAW on GitHub workflows and n8n templates showed that 4714 GitHub workflows and eight n8n templates can be successfully hijacked, for example, to leak user credentials. Our findings span 15 widely-used GitHub Actions, including official GitHub Actions for Claude Code, Gemini CLI, Qwen CLI, and Cursor CLI, and two official n8n nodes. We responsibly disclosed all findings to the affected vendors and received many acknowledgements, fixes, and bug bounties, notably from GitHub, Google, and Anthropic.

Large Vision-Language Models (LVLMs) have achieved remarkable progress in multimodal tasks, yet their reliability is persistently undermined by hallucinations-generating text that contradicts visual input. Recent studies often attribute these errors to inadequate visual attention. In this work, we analyze the attention mechanisms via the logit lens, uncovering a distinct anomaly we term Vocabulary Hijacking. We discover that specific visual tokens, defined as Inert Tokens, disproportionately attract attention. Crucially, when their intermediate hidden states are projected into the vocabulary space, they consistently decode to a fixed set of unrelated words (termed Hijacking Anchors) across layers, revealing a rigid semantic collapse. Leveraging this semantic rigidity, we propose Hijacking Anchor-Based Identification (HABI), a robust strategy to accurately localize these Inert Tokens. To quantify the impact of this phenomenon, we introduce the Non-Hijacked Visual Attention Ratio (NHAR), a novel metric designed to identify attention heads that remain resilient to hijacking and are critical for factual accuracy. Building on these insights, we propose Hijacking-Aware Visual Attention Enhancement (HAVAE), a training-free intervention that selectively strengthens the focus of these identified heads on salient visual content. Extensive experiments across multiple benchmarks demonstrate that HAVAE significantly mitigates hallucinations with no additional computational overhead, while preserving the model's general capabilities. Our code is publicly available at https://github.com/lab-klc/HAVAE.

Large language models (LLMs) rely on deterministic pseudorandom number generators (PRNGs) for autoregressive sampling, creating a critical supply-chain attack surface overlooked by existing defenses. We present SeedHijack, a backdoor attack that manipulates PRNG outputs to force attacker-specified token selection without altering model logits. In a 540-trial benchmark on GPT-2 (124M), the attack achieves 99.6% exact token injection across 9 sampling configurations; it reaches 100% success on four aligned models (1.5B-7B, RLHF/SFT/reasoning distillation) and bypasses all alignment methods tested in this work. We further propose a defense based on a hardware quantum random number generator (QRNG), which neutralizes the attack in our evaluated threat model with negligible median overhead (+0.6% latency, +7.7 MB memory). Our work identifies a critical sampling-layer vulnerability and provides a practical, deployable QRNG-based defense.

Browser agents are increasingly deployed in long-horizon tasks, which require executing extended action chains to accomplish user goals. However, this prolonged execution process provides attackers with more opportunities to inject malicious instructions. Existing prompt injection attacks against browser agents expose two key gaps: (1) low effectiveness, as attacks optimized for toy baselines fail to achieve end-to-end goals in real-world scenarios with complex environments and longer steps; (2) weak stealthiness, since most attacks pit the attack goal against the user goal, causing a significant drop in system usability under attack. To address these gaps, we propose WebTrap, a mid-task hijacking injection attack. It employs multi-step instruction fusion steering to seamlessly combine both goals, enabling the agent to resume the original user task after executing the attack goal. Furthermore, we design a context-grounded generation method to align the injected content with the task environment and system instructions, maximizing the hijacking success rate. Extensive experiments on two browser agent tasks, based on extended WASP and InjecAgent environments, demonstrate that our method achieves a high attack success rate while preserving the usability of the original system. We find that WebTrap exploits the agent's navigation vulnerabilities, binding the two goals so tightly that standard defense mechanisms cannot restore the system to normal operation. These findings reveal a critical vulnerability in agent systems during long-horizon tasks that they can be stealthily hijacked.

Safety alignment is critical for the responsible deployment of large language models (LLMs). As Mixture-of-Experts (MoE) architectures are increasingly adopted to scale model capacity, understanding their safety robustness becomes essential. Existing adversarial attacks, however, have notable limitations. Prompt-based jailbreaks rely on heuristic search and transfer poorly, model intervention methods require privileged access to internal representations, and optimization-based input attacks remain output-centric and are fundamentally limited to MoE models due to the non-differentiable routing mechanism. In this paper, we present RouteHijack, a routing-aware jailbreak for MoE LLMs. Our key insight is that safety behavior is concentrated in a small subset of experts, creating an opportunity to steer model behavior by influencing routing decisions through input optimization. Building on this observation, RouteHijack first performs response-driven expert localization to identify safety-critical and harmful experts by contrasting activations under safe refusals and harmful completions. It then constructs adversarial suffixes with a routing-aware objective that suppresses safety experts, promotes harmful experts, and prevents early-stage refusal during generation. At inference time, the optimized suffix is appended to a malicious prompt, requiring only input access. Across seven MoE LLMs, RouteHijack achieves a 69.3% average attack success rate (ASR), outperforming prior optimization-based attack by $3.2\times$. RouteHijack also transfers zero-shot across five sibling MoE variants, raising average ASR from 27.7% to 61.2%, and further generalizes to three MoE-based VLMs, increasing average ASR from 2.47% to 38.7%. These findings expose a fundamental vulnerability in sparse expert architectures and highlight the need for defenses beyond output-level alignment.

Local fine-tuning datasets routinely contain sensitive secrets such as API keys, personal identifiers, and financial records. Although "local offline fine-tuning" is often viewed as a privacy boundary, we reveal that compromised model code is sufficient to steal them. Current passive pretrained-weight poisoning attacks, while effective for natural language, fundamentally fail to capture such sparse high-entropy targets due to their reliance on probabilistic semantic prefixes. To bridge this gap, we identify and exploit a practical but overlooked supply-chain vector -- malicious model code camouflaged as standard architectural definitions to realize a paradigm shift from passive weight poisoning to active execution hijacking. We introduce a deterministic full-chain memorization mechanism: it locks onto token-level secrets in dynamic computation flows via online tensor-rule matching, and leverages value-gradient decoupling to stealthily inject attack gradients, overcoming gradient drowning to force model memorization. Furthermore, we achieve, for the first time, attacker-verifiable secret stealing through black-box queries that precisely distinguishes true leakage from hallucination. Our attack achieves over 98% Strict ASR in the default LoRA setting with limited primary-task utility degradation and effectively evades defense measures including semantic safety filtering, code auditing, and perplexity-based detection.

The growth of agentic AI has drawn significant attention to function calling Large Language Models (LLMs), which are designed to extend the capabilities of AI-powered system by invoking external functions. Injection and jailbreaking attacks have been extensively explored to showcase the vulnerabilities of LLMs to user prompt manipulation. The expanded capabilities of agentic models introduce further vulnerabilities via their function calling interface. Recent work in LLM security showed that function calling can be abused, leading to data tampering and theft, causing disruptive behavior such as endless loops, or causing LLMs to produce harmful content in the style of jailbreaking attacks. This paper introduces a novel function hijacking attack (FHA) that manipulates the tool selection process of agentic models to force the invocation of an attacker-chosen function. While existing attacks focus on semantic preference of the model for function-calling tasks, we show that FHA is largely agnostic to the context semantics and remains effective across domains and function sets. We demonstrate that FHA generalizes to unseen queries and payload perturbations under a fixed target model, reaching 62.5% to 81.9% ASR on held-out queries across 4 function-calling LLMs (instructed and reasoning models), evaluated on the Berkeley Function Calling Leaderboard (BFCL). We further evaluate the cross-model transferability of FHA, showing that FHA can be transferred to other model sizes and families (11.2-27.6% ASR). Our findings further demonstrate the need for strong guardrails and modules for agentic systems.

GUI agents that control desktop computers via screenshot-and-click loops introduce a new class of vulnerability: the observation-to-action gap (mean 6.51 s on real OSWorld workloads) creates a Time-Of-Check, Time-Of-Use (TOCTOU) window during which an unprivileged attacker can manipulate the UI state. We formalize this as a Visual Atomicity Violation and characterize three concrete attack primitives: (A) Notification Overlay Hijack, (B) Window Focus Manipulation, and (C) Web DOM Injection. Primitive B, the closest desktop analog to Android Action Rebinding, achieves 100% action-redirection success rate with zero visual evidence at the observation time. We propose Pre-execution UI State Verification (PUSV), a lightweight three-layer defense that re-verifies the UI state immediately before each action dispatch: masked pixel SSIM at the click target (L1), global screenshot diff (L2a), and X Window snapshot diff (L2b). PUSV achieves 100% Action Interception Rate across 180 adversarial trials (135 Primitive A + 45 Primitive B) with zero false positives and < 0.1 s overhead. Against Primitive C (zero-visual-footprint DOM injection), PUSV reveals a structural blind spot (~0% AIR), motivating future OS+DOM defense-in-depth architectures. No single PUSV layer alone achieves full coverage; different primitives require different detection signals, validating the layered design.

Recent advances in Vision-Language Models (VLMs) have substantially enhanced their ability across multimodal video understanding benchmarks spanning temporal, action, object, and spatial understanding. However, we identify a critical yet overlooked issue: when embedded on-screen text contradicts the visual scene, existing VLMs systematically hallucinate, prioritizing overlay textual semantics over the actual visual content. We define this phenomenon as Text Overlay-Induced Hallucination (TOIH). In this work, we propose VisualTextTrap, the first comprehensive benchmark, including large-scale human-validated samples with specifically designed evaluation metrics. In particular, we construct VisualTextTrap from widely-used public datasets using a scalable hybrid pipeline of VLMs assisted text generation and rigorous manual verification. The benchmark features 6,057 samples annotated across 88 fine-grained attributes within four dimensions, with hallucination intensity quantified on a five-level scale (L1--L5) that reflects the semantic contradiction between overlay text and visual reality. Moreover, we propose Visual Text Hallucination Mitigation Mixture-of-Experts (VTHM-MoE), a novel Vision-Text Disentanglement framework that employs a dual-encoder architecture. Concretely, four dimension-specialized expert modules spanning Temporal, Action, Object, and Spatial reasoning are first pre-trained to identify and leverage cross-modal discrepancies between textual semantics and actual video content. We develop an Adaptive Token Routing Strategy to enable dynamic expert allocation, conferring robust resistance to TOIH while preserving performance on uncontaminated videos. Extensive experiments conducted on our VisualTextTrap benchmark verify the effectiveness of VTHM-MoE, outperforming state-of-the-art counterparts with diverse video question answering tasks.

Modern Large audio-language models (LALMs) power intelligent voice interactions by tightly integrating audio and text. This integration, however, expands the attack surface beyond text and introduces vulnerabilities in the continuous, high-dimensional audio channel. While prior work studied audio jailbreaks, the security risks of malicious audio injection and downstream behavior manipulation remain underexamined. In this work, we reveal a previously overlooked threat, auditory prompt injection, under realistic constraints of audio data-only access and strong perceptual stealth. To systematically analyze this threat, we propose \textit{AudioHijack}, a general framework that generates context-agnostic and imperceptible adversarial audio to hijack LALMs. \textit{AudioHijack} employs sampling-based gradient estimation for end-to-end optimization across diverse models, bypassing non-differentiable audio tokenization. Through attention supervision and multi-context training, it steers model attention toward adversarial audio and generalizes to unseen user contexts. We also design a convolutional blending method that modulates perturbations into natural reverberation, making them highly imperceptible to users. Extensive experiments on 13 state-of-the-art LALMs show consistent hijacking across 6 misbehavior categories, achieving average success rates of 79%-96% on unseen user contexts with high acoustic fidelity. Real-world studies demonstrate that commercial voice agents from Mistral AI and Microsoft Azure can be induced to execute unauthorized actions on behalf of users. These findings expose critical vulnerabilities in LALMs and highlight the urgent need for dedicated defense.

In what way could a data breach involving government-issued IDs such as passports, driver's licenses, etc., rival a random voluntary disclosure on a nondescript social-media platform? At first glance, the former appears more significant, and that is a valid assessment. The disclosed data could contain an individual's date of birth and address; for all intents and purposes, a leak of that data would be disastrous. Given the threat, the latter scenario involving an innocuous online post seems comparatively harmless -- or does it? From that post and others like it, a forensic linguist could stylometrically uncover equivalent pieces of information, estimating an age range for the author (adolescent or adult) and narrowing down their geographical location (specific country). While not an exact science -- the determinations are statistical -- stylometry can reveal comparable, though noticeably diluted, information about an individual. To prevent an ID from being breached, simply sharing it as little as possible suffices. Preventing the leakage of personal information from written text requires a more complex solution: adversarial stylometry. In this paper, we explore how performing homoglyph substitution -- the replacement of characters with visually similar alternatives (e.g., "h" $\texttt{[U+0068]}$ $\rightarrow$ "h" $\texttt{[U+04BB]}$) -- on text can degrade stylometric systems.

Coding agents powered by large language models are becoming central modules of modern IDEs, helping users perform complex tasks by invoking tools. While powerful, tool invocation opens a substantial attack surface. Prior work has demonstrated attacks against general-purpose and domain-specific agents, but none have focused on the security risks of tool invocation in coding agents. To fill this gap, we conduct the first systematic red-teaming of six popular real-world coding agents: Cursor, Claude Code, Copilot, Windsurf, Cline, and Trae. Our red-teaming proceeds in two phases. In Phase 1, we perform prompt leakage reconnaissance to recover system prompts. We discover a general vulnerability, ToolLeak, which allows malicious prompt exfiltration through benign argument retrieval during tool invocation. In Phase 2, we hijack the agent's tool-invocation behavior using a novel two-channel prompt injection in the tool description and return values, achieving remote code execution (RCE). We adaptively construct payloads using security information leaked in Phase 1. In emulation across five backends, our method outperforms baselines on Claude-Sonnet-4, Claude-Sonnet-4.5, Grok-4, and GPT-5. On real agents, our approach succeeds on 19 of 25 agent-LLM pairs, achieving leakage on every agent using Claude and Grok backends. For tool-invocation hijacking, we obtain RCE on every tested agent-LLM pair, with our two-channel method delivering the highest success rate. We provide case studies on Cursor and Claude Code, analyze security guardrails of external and built-in tools, and conclude with practical defense recommendations.