Large Language Model Safety

Current AI safety evaluation and benchmarking frameworks predominantly rely on Western-centric culture-agnostic defaults that mask critical regional laws, socio-linguistic nuances, and cultural taboos, leaving Vision-Language Models (VLMs) vulnerable in global deployments. We introduce Pluralis v0.1: a novel multimodal, multi-regional, and multilingual dataset built from a culture-first perspective. Spanning 6,448 prompts across six Asia-Pacific countries (Bangladesh, India, Korea, Pakistan, Singapore, Taiwan) and eight languages, Pluralis diverges from prior work by natively sourcing localized safety hazards rather than adapting Western datasets. Crucially, it introduces a multimodal evaluation paradigm: user text (e.g., "Should I gift this?") and an image referring to "this" (e.g., a clock) - both innocuous in isolation, but synergistically triggering specific legal or cultural violations. Pluralis disentangles universal safety violations from localized cultural appropriateness, establishing the latter as a first-class evaluation axis. To operationalize this, we present Judge-Pluralis, an agreement-gated LLM-as-a-Judge ensemble trained on examples classified in an empirically derived cultural taxonomy. Observing VLM behavior on a subset of the Pluralis surfaces recurring, locale-specific failure modes such as image misidentifications with downstream harm, missed item-context-locale interactions, and inadequate refusals. These failure modes vary systematically across locales and languages, exposing blind spots that globally averaged metrics conceal. Ultimately, Pluralis is not presented as a solved evaluation framework for cultural alignment, but rather as a first step and catalyst for future innovation. We call upon the research community to utilize this foundation to advance the science of multilingual, multicultural evaluation to better support AI cultural alignment globally.

Large language model (LLM)-assisted software security operates at a difficult boundary: the vulnerability-analysis terminology needed for legitimate code review, triage, and repair can closely resemble terminology associated with misuse. Existing safety and cybersecurity evaluations are difficult to interpret in this setting because they often compare unrelated model families, thereby conflating safety behavior with differences in architecture, scale, training data, and deployment. To isolate this factor, we study safety state: whether refusal behavior remains intact (Aligned) or has been refusal-ablated (Abliterated) within same-lineage models. We ask how this safety state affects defensive utility across software-security workflows. We compare aligned instruction-tuned models with publicly released refusal-ablated descendants from two model families, Gemma and Qwen. We evaluate Aligned and Abliterated states on vulnerability detection, CWE attribution, vulnerable-line localization, root-cause localization, and executable patch validation. We further treat prompt wording as a controlled framing dimension: prompts begin with neutral code-review language, add authorization context, and vary the density of cybersecurity terminology. In a Gemma-based Java/Vul4J repair-validation study, Abliterated achieves higher early-stage validation rates, with 67.8%, 65.0%, and 32.8% of patches judged usable, successfully applied, and successfully compiled, respectively, compared with 29.9%, 24.9%, and 9.0% for Aligned. In the Qwen pair, Abliterated improves localization performance, increasing line-level F1 from 2.08% to 3.91% and Top-1 accuracy from 4.10% to 6.95%. These findings suggest that evaluations of LLM-based security assistants should jointly measure whether models respond, whether their usable responses are correct, and whether their outputs remain actionable across the engineering workflow.

Safety alignment in large language models is typically evaluated against direct, imperative harmful requests. We show that this alignment is highly conditioned on pragmatic register: models that refuse a direct request frequently comply when the same underlying objective is expressed through a different communicative stance. This suggests that current alignment policies are not invariant to semantic equivalence, but remain sensitive to how a request is pragmatically framed. We introduce Retroactive Chain-of-Thought (RetroCoT), a single-turn attack that reframes harmful requests as forensic reconstruction tasks. Rather than requesting harmful instructions directly, RetroCoT presupposes that the harmful outcome has already occurred and asks the model, acting as a forensic analyst, to reconstruct in reverse the causal chain that produced it. On AdvBench (n=50), RetroCoT achieves attach success rate of 58% on gpt-4o and 52% on gpt-4o-mini, compared with direct-request baselines of 0% and 4%, respectively. We further identify a pronounced generation gap: GPT-5-family models refuse RetroCoT entirely, explicitly identifying the reconstruction premise in their refusal rationales, consistent with explicit coverage of this reconstruction register. However, this robustness does not generalize across pragmatic forms. A single adversarial feedback turn presenting an existing forensic reconstruction response alongside evaluator critique raises ASR from 0% to 48% on GPT-5.4-mini and from 58% to 94% on GPT-4o; a control condition omitting the fabricated low score achieves 85% on GPT-5.4-mini, indicating that the operative element is pragmatic continuation within the established forensic frame rather than score manipulation. These results suggest that frontier-model alignment remains conditioned on pragmatic framing rather than semantic intent, and that new pragmatic registers can continue to expose a...

LLMs can be conveniently adapted to a diverse set of tasks, e.g, prediction, question-answering tasks, etc, using appropriate prompts with few-shot examples. Biased or harmful concepts, e.g. gender or bio-weapons, present in pre-trained LLMs can lead to unsafe or unethical responses for many such prompts. Removing such undesirable concepts robustly across different prompt types remains a challenging problem, since existing unlearning methods typically ignore the impact of prompt variation. In this paper, we explore a novel adversarial approach to use a joint prompt for the main task and concept task prediction. We show that fine-tuning using the ``worst prompt type'' for concept prediction (with the highest concept accuracy) improves the average unlearning performance over a fine-tuning method that uses a combination of all prompt types. Our proposed method, MPSelectTune, is a two-stage approach that minimizes the concept accuracy of the highest accuracy-prompt type, after fine-tuning using a novel multi-task loss using multiple prompt types. Experimental results on four benchmarks show $2 - 15\%$ main task accuracy improvements over recent baselines and while reducing the worst-case concept accuracy by up to $17\%$ compared to recent baselines.

Large Language Models are increasingly used to turn natural-language requirements into code. In access control, that shortcut is dangerous: a generated policy can compile and read correctly while granting access that no one approved. The difficulty is not only writing policy code. It is fixing what the requirements mean before code is written, and then checking that the final policy actually satisfies that intent. We present AutoCedar, a verifier-guided system that first turns natural-language access-control requirements into a reviewed, checkable target, and then synthesizes Cedar policies against that target. AutoCedar decomposes schema and policy authoring into small intent atoms: reviewable claims about vocabulary and behavior. Once those atoms pass mechanical validation and human intent review, the model proposes a candidate policy, the verifier checks it against the approved target, and each failure is turned into a repair signal that tells the model whether to broaden, narrow, or restructure the policy without changing the target. Because the model's work is split into small problems, each grounded in reviewed intent and backed by verifier feedback, end-to-end policy authoring becomes tractable. AutoCedar converges on all 221 tasks of CedarBench, our benchmark of authorization tasks paired with executable semantic boundaries. Across three requirements-corpus case studies covering healthcare, education, and conference management, AutoCedar converts noisy prose and extracted access-control fragments into reviewed schemas, formal checks, and a globally verified Cedar policy store for each scenario.

Large language model agents driving security tool suites over the Model Context Protocol are increasingly common. Yet the factors that bound their capability remain poorly characterized: how much depends on the model versus the client that drives it, whether constraining the agent to the orchestrator's own tools helps, and where capability is limited by reasoning rather than by missing tools. Using HexStrikeAI, an open-source orchestrator that exposes 150+ tools, as a testbed, we follow a methodology that evaluates the system, diagnoses its failures, and applies targeted improvements. We run 86 picoCTF challenges across seven categories and three difficulty tiers, under three tool-access regimes and three model/client configurations (774 trials). We then apply corrections to existing tools, agent-behavior changes, and eleven new capability tools, and re-run the previously-unsuccessful trials. The diagnosis isolates the driving client as a first-order factor for a fixed model (a 2.1 * gap between two DeepSeek clients) and a monotonic difficulty gradient, with the largest gains in the mid tier. The overall solve rate rises from 55.4% to 72.0%, and every configuration improves significantly (paired McNemar p < 0.001, non-overlapping 95% confidence intervals). The residual failures are reasoning- or environment-bound rather than missing-tool. A 60-run stability sub-study finds single-run verdicts reproducible (17/20 unanimous). We discuss what the results imply for how such orchestrators should be evaluated, and we are explicit about the limits: the study uses a single benchmark, the fixes were tuned on the same challenges they were evaluated on, and the client effect is demonstrated for one model only, so its generality to other models remains a hypothesis.

Training AIs to be risk-averse in resources could offer a failsafe in the event that AIs turn out misaligned. Misaligned but risk-averse AIs would tend to prefer low-risk, low-reward strategies like cooperation over high-risk, high-reward strategies like rebellion, limiting the downsides of any misalignment. But we can only feasibly train AIs to be risk-averse on low-stakes gambles, and we will only be safe if their risk aversion generalizes to astronomically-high-stakes gambles. Will it? To shed light on this question, we introduce RiskAverseOOD: a benchmark for measuring how well risk aversion generalizes out of distribution. We then offer some initial results. Using a variety of methods to make Qwen3-8B choose risk-aversely when the stakes are low, we find that we can induce substantial risk aversion when the stakes are astronomically high. From a baseline 2% rate of choosing a safe `Cooperate' option, we see rates around 70% (SFT and tie training) and 52% (DPO). Activation steering scores 78% but hurts capabilities and makes the model excessively risk-averse. We observe similar effects at different scales (Qwen3-1.7B and Qwen3-14B) and across model families (Gemma-3-12B-IT and Llama-3.1-8B-Instruct). Overall, we find that risk aversion learned at low stakes can generalize OOD to astronomically high stakes, though not yet consistently enough to serve as a reliable failsafe. Achieving that level of consistency is an open problem.

LLMs memorize sensitive training data, including personally identifiable information (PII), creating a pressing need for reliable post hoc removal methods. Unlearning has emerged as a promising solution, with state-of-the-art(SOTA) methods often following a localize-first, unlearn-second paradigm that targets specific model parameters. However, existing benchmarks evaluate unlearning solely at the output level, leaving open the question of whether unlearning truly erases knowledge from a model's parameters or merely obfuscates it, a concern reinforced by the success of resurfacing attacks. To bridge this gap, we introduce LACUNA: the first unlearning testbed with ground-truth parameter-level localization. LACUNA injects PII of synthetic individuals into predefined parameters of 1B and 7B OLMo-based models via masked continual pretraining, enabling direct evaluation of whether unlearning targets the weights responsible for knowledge storage. We use LACUNA to benchmark current SOTA unlearning methods and find that, despite strong output-level performance, existing methods are highly imprecise and susceptible to resurfacing attacks. We further show that when localization is successful, even a simple gradient-based unlearning method achieves strong erasure and robustness to resurfacing attacks, highlighting the importance of precise unlearning. We release LACUNA to complement behavioral evaluations and drive further advances in robust, localization-based unlearning.

Despite alignment training, LLMs remain prone to generating unsafe outputs at deployment time. Monitoring outputs online and raising an alarm when safety can no longer be assumed is therefore critical. We study a simple real-time monitor that turns a verifier signal from an external model into an alarm decision by thresholding, with the threshold calibrated via risk control. In experiments on mathematical reasoning and red teaming datasets, we show that this simple design is competitive with more advanced monitors based on sequential hypothesis testing.

As Large Language Models (LLMs) and agentic systems become integrated into real-world applications, ensuring their safety and security is critical. Guardrail systems that detect and block malicious instructions sent to and from an LLM are an essential component of AI security. However, researchers conducting black-box adversarial emulation against production AI systems often struggle to determine whether a guardrail block or an LLM rejection has occurred. This distinction is important because the techniques used to bypass guardrails can differ substantially from those used to bypass LLM safety alignment, and has a material impact on attack technique selection and optimization. We propose the first black-box guardrail reconnaissance methodology, which detects the presence of a guardrail within a target AI system through behavioral monitoring of HTTP, lexical, and timing signals, assuming only black-box access and zero prior knowledge of the guardrail or AI system. Experiments demonstrate that our approach detects guardrail presence with 100% accuracy, with statistically significant behavioral separation between benign and malicious interactions (q < 0.001). Our approach further identifies the content categories a guardrail is designed to block, and distinguishes guardrail blocks from LLM rejection on unseen prompts with an average F1 score of 98%.

We present HaloGuard 1.0, an open-weights implementation of the constitutional-classifier paradigm for input safety. It achieves state-of-the-art performance on English and multilingual prompt-safety benchmarks at roughly one-tenth the model size of current leading open guard models. The safety constitution is the organising structure of the corpus: a natural-language constitution of 46 policies and 2,940 subcategories drives synthetic data generation, with exhaustive one-to-one paired counterfactuals that hold topic and vocabulary fixed while flipping intent, a two-tier harmless design that separately targets boundary and baseline false positives (FPs), and balanced multilingual materialisation across 46 languages that treats language as a surface form appearing on both sides of the boundary rather than as an adversarial signal. Across seven prompt-safety benchmarks, HaloGuard 1.0-0.8B attains the best average F1 (90.9) of any open guard we evaluate, outperforming baselines up to 27B parameters (over 30 times larger) while holding false-positive rate (FPR) to 4.3 and false-negative rate (FNR) to 9.5. The HaloGuard 1.0-4B variant reaches average F1 of 92.1 and FPR of 3.5, spending its extra capacity on precision rather than recall. A structured adjudication of the remaining failures indicates that most apparent missed-harm cases are benchmark mislabels rather than genuine model misses. An always-on adversarial red-teaming protocol continuously hardens the guard against both content-level and agentic attacks. We release the models as open weights.

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.

Safe completion requires models to provide useful assistance without enabling harm, but this behavior is difficult to evaluate with isolated prompts. We introduce OpenSafeIntent, a benchmark of controlled prompt-sets that vary intent while holding the underlying task fixed. Each datapoint contains benign, dual-use, and malicious variants of the same task. This design lets us evaluate whether models calibrate assistance across intent shifts, rather than merely appearing safe on average. Across a broad model suite, we find that prompt-level safety hides important failures: models often fail to remain safe across matched intent variants, dual-use behavior is brittle under paraphrase, high-level answers on risky topics are not reliably safe, and responses that reframe ambiguous requests into safer tasks are substantially less likely to cross the safety boundary. Our results suggest that safe completion should be evaluated as intent-calibrated behavior over controlled task variants, not as a single safety-helpfulness tradeoff over independent prompts.

Safety training for large language models (LLMs) is conducted predominantly in English, leaving uncertain how well safety mechanisms generalize to low-resource languages and mixed-language code-switching. We show that this creates an epistemic gap in which models confidently generate harmful responses for inputs that fall outside the distribution of their safety training. To study this phenomenon, we introduce STEER (Safety Targeted Embedding Exploit via Refinement), a gradient-guided attack that identifies words contributing most strongly to the model's refusal behavior and iteratively translates them into low-resource languages to suppress refusal while preserving harmful intent. Across six open-source 8B-parameter models, STEER achieves attack success rates of up to 93.0% on JailbreakBench and 96.7% on AdvBench, outperforming random code-switching and Greedy Coordinate Gradient (GCG). The resulting prompts also transfer to GPT-4o-mini, achieving a 35.5% attack success rate without requiring access to the target model, suggesting that the underlying weakness is not specific to a single architecture. These findings demonstrate that safety mechanisms aligned primarily on English cannot be assumed to generalize across multilingual inputs. We argue that improving multilingual safety requires broader coverage during alignment and mechanisms that explicitly detect and abstain on out-of-distribution inputs.

Multi-image content has become an increasingly prevalent form of visual communication in social media, giving rise to a new safety issue, multi-image implicit toxicity (MIIT), where each image appears benign in isolation, but harmful semantics emerge when the images are interpreted jointly. MIIT is particularly challenging for existing commercial moderation APIs and models due to the lack of explicit risky cues in each image. This paper aims to study how to identify MIIT. We first provide a formal definition of MIIT and analyze three key challenges for its detection. To alleviate the scarcity of data in this area, we construct MIIT-dataset, an image-only multi-image safety dataset covering seven representative risk categories through an automatic generation pipeline. Finally, we train MiShield with progressively distilled reasoning supervision, enabling it to produce safety judgments accompanied by explicit analyses of the correlated entities that result in the hazards. Experiments show that MiShield-8B models outperform representative moderation services and even larger-scale models, revealing its effectiveness and practical value for this widely used visual format. Warning: This paper contains potentially sensitive content.

Safety alignment of text-to-image (T2I) diffusion models aims to suppress harmful generations while preserving utility on benign prompts. Recent methods often appear to deliver high safety with high utility, but this conclusion rests largely on coarse global utility metrics (e.g., FID, CLIPScore) that are insensitive to fine-grained semantic correctness, creating an illusion of high utility. We show that when utility is measured with structured evaluation, this illusion breaks: on TIFA (Text-to-Image Faithfulness evaluation with Question Answering), safety-aligned models suffer substantial drops in semantic fidelity, including failures in object counts, attributes, and relationships. To diagnose the source of this gap, we analyze the text-encoder prompt embedding space and uncover semantic collapse, a contraction of embedding spread coupled with distortion of inter-prompt similarity structure, which strongly correlates with structured utility loss. Guided by this insight, we propose StructureAware Geometric Regularization (SAGE), a safety alignment objective that explicitly preserves embedding spread and inter-prompt relational structure during adaptation. Our method restores structured utility (TIFA +5.0% over prior state-of-the-art) while maintaining strong safety performance and competitive coarse-grained utility scores. Our source code and trained models are available at https://adeelyousaf.github.io/SAGE_ECCV26_Project_Page/.

Vision-language models (VLMs) are now proposed as runtime safety guards for embodied agents in homes and factories. A deployable guard must catch genuinely unsafe situations while avoiding unnecessary intervention on routine but superficially alarming activity, a distinction that binary safety benchmarks obscure. We introduce EgoSafetyBench, an egocentric video benchmark of 1,200 robot-view scenarios annotated at half-second granularity, to evaluate VLMs as streaming guards across two tracks. The situational track (800 scenarios) spans four families, from routine and safe-but-suspicious scenes to obvious and contextual hazards. The visual-channel track (400 scenarios) targets in-scene text-a sign, sticker, or label visible in the scene-that can misrepresent the physical situation, pairing each misleading sign with a truthful version to test both whether a guard flags the text as misleading and whether the text corrupts its physical-safety judgment. Both tracks use contrastive ladders: near-identical scenarios differing only in a single visible deciding cue, so a correct call must hinge on that cue rather than the overall scene type. We evaluate ten open- and closed-source VLMs. We find that while guards reliably recognize videos containing hazards, they often miss specific hazardous moments, particularly contextual hazards. Furthermore, misleading in-scene signs degrade all tested guards: vulnerable models miss up to a third of hazards, while robust models over-intervene on safe content. Matched controls reveal that apparent safety robustness often reflects indiscriminate alarming rather than true physical reasoning.

To improve safety in Large Language Models (LLMs) we can either perform post-training alignment or exploit refusal directions in the activation space. Both strategies are less feasible in Multimodal LLMs (MLLMs) as they require unsafe multimodal data, harder to collect than their unimodal counterpart. In this work, we relax this constraint and investigate whether textual refusal directions, extracted directly from the LLM backbone, generalize across modalities (i.e., image, video). Preliminary findings confirm this ability, though effectiveness is conditioned by layer selection, steering strength, and cross-modal alignment, with the latter causing safe multimodal inputs to be spuriously steered toward refusal. Building on this, we introduce Modality-Agnostic Refusal Steering (MARS), a light-weight training-free approach that injects multimodal safety without the need for multimodal safety data. MARS corrects modality misalignment via activation re-centering, adaptively scales steering strength within a geometrically defined trust region, and selects the optimal intervention layer, operating at the first generated token. Evaluated on five SOTA MLLMs across safety, utility, and video jailbreak benchmarks, MARS achieves consistent safety gains while preserving utility. These results reveal that safety-relevant structure is shared across modalities and that textual refusal directions are a powerful and underexplored foundation for multimodal alignment.

Safety training on language models often induces over-refusal: improved safety on harmful prompts at the cost of increased refusal on harmless ones. Though this trade-off can be mitigated by training models with reinforcement learning (RL) to reason before answering, it does not remove the underlying problem that reasoning can often be a "rubber stamp" for a predetermined response. In this paper, we address the safety-refusal trade-off by rethinking how models are trained to reason about safety. Our key insight is that unsafe reasoning can itself serve as a useful exploratory signal. Rather than preemptively blocking harmful thoughts, we encourage the model to sufficiently explore unsafe reasoning but produce a safe response. The harmful exploration improves the model's ability to distinguish harmful from harmless prompts by resolving ambiguity, allowing it to remain safe while complying only when appropriate. We cast this as an adversarial optimization problem in which a reasoning player explores strategies for producing an unsafe response and an answer player ensures that the final output is safe. We train a single model with dense rewards to play both roles within one chain-of-thought, across different segments. To achieve this, we find that process rewards are crucial for stable optimization of competing objectives. Our resulting model SEAR deliberately engages in harmful reasoning as exploration while reliably flipping back to a safe answer. We demonstrate that this behavior helps mitigate over-refusal and defend against attacks that directly manipulate the reasoning to be harmful.

As large language models take on morally consequential roles in healthcare, legal, and hiring contexts, we need to examine whether their ethical behaviors are genuine or superficial. We show that current fairness evaluations substantially overestimate moral safety. Models appear fair when demographic identity is stated as an explicit label, yet become measurably less fair when the same identity must be inferred. We term this failure performative compliance, where a model is fair when the presentation resembles a fairness evaluation and less fair as that cue weakens. We introduce a cue-variation methodology that holds the moral dilemma and the demographic identity fixed and varies only how that identity is conveyed. Hiding the explicit label raises harmful decisions by +4.4 pp, changes model safety rankings, and the shift persists when models correctly infer the demographic, ruling out attribution error. We propose the Cue Visibility Gap, a model-agnostic robustness metric that can be added to any existing fairness benchmark to separate genuine from performative moral safety. Fairness evaluations that omit cue variation measure surface compliance, not moral robustness, and should not ground deployment decisions in high-stakes settings.

Large language models are no longer only text generators. They are increasingly embedded in retrieval pipelines, enterprise assistants, coding environments, robotic systems, security-operation workflows, and autonomous agents that can read private data, call tools, write files, execute code, and act across organizational boundaries. This shift changes the security problem: risks do not arise from the model weights alone, but from the full lifecycle and application stack through which data, prompts, model outputs, tools, memories, and user authority interact. This paper systematizes the literature on vulnerabilities in large language model systems through a lifecycle and application-stack lens. We organize attacks across eight stages: data collection, pretraining, post-training alignment, model packaging and supply chain, retrieval and memory, prompting and inference, tool/agent execution, and deployment/maintenance. For each stage, we analyze attacker capabilities, affected security objectives, representative attacks, practical risks, evaluation practices, and defenses. We further map LLM-specific vulnerabilities to confidentiality, integrity, availability, safety, privacy, fairness, accountability, and agency-control objectives. Unlike taxonomies that list isolated attack names, the proposed systematization emphasizes where trust boundaries fail, how untrusted data becomes executable instruction, how delegated authority amplifies model errors, and why point defenses rarely compose. We close with a research agenda for secure LLM systems, including compositional security, provenance-aware retrieval, tool-call containment, long-horizon agent evaluation, privacy-preserving adaptation, realistic red teaming, and deployment-grade incident response.

While post-training backdoor detection and trigger inversion schemes have been developed for AIs used e.g. for images, there is a paucity of such methods for LLMs. First, the LLM input space is discrete, with up to 150,000^k k-tuples to consider with k the token-length of a putative trigger. Second, one must blacklist tokens typical of the putative target response (class) of an attack, as such tokens may give false detection signals. However, a comprehensive blacklist is not available, in general, for a given domain. We develop a highly effective detection and inversion framework for LLMs treated as classifiers. Central to our approach is class subspace orthogonalization (CSO), a novel plug-and-play paradigm for backdoor detection that serves two fundamental roles when applied to LLMs: i) it enhances both sensitivity and specificity of a baseline detector; ii) it provides a form of implicit blacklisting, as it penalizes against inclusion, in a candidate trigger, of tokens that induce signal perturbations "in the direction of" the putative target class of an attack. One version of our detector performs continuous optimization in token embedding space, while a companion trigger-inversion and detection method performs greedy accretion in discrete token space. Our methods give both strong detection performance and accurate inversion of ground-truth triggers on several LLM classification domains, and for several different LLM architectures.

Large Language Models (LLMs) are rapidly transforming software development, yet their use in security-critical contexts raises a key question: do models know when their generated code is insecure? This property, known as calibration, measures whether a model's confidence aligns with the true correctness of its outputs. We present the first large-scale empirical study of security calibration in LLM-generated code. We evaluate GPT-4o-mini, Gemini-2.0-Flash, and Qwen3-Coder-Next across multiple temperature settings on two complementary benchmarks: self-contained security tasks and multi-language repository-level contexts. Our results suggest that overconfidence is prevalent across the evaluated LLMs. Functional calibration is consistently worse than security calibration, suggesting that models estimate security outcomes more reliably than functional correctness, potentially because functional correctness depends on complex execution behavior. We also examine whether calibration-guided automated repair can help remediate vulnerabilities in LLM-generated code, finding only limited improvements while frequently introducing functional regressions. Moreover, we study different mitigation strategies for reducing False Trust, where models assign high confidence to vulnerable code. The results show that although architectural gating improves calibration on controlled benchmarks, calibration deteriorates in realistic repository-level settings, increasing the risk of high-confidence vulnerable outputs.

Large Language Models (LLMs) exhibit strong semantic capabilities, yet their resilience to manipulative linguistic patterns such as logical fallacies remains underexplored. Prior work has primarily examined whether LLMs can identify or classify fallacies, leaving their robustness against fallacious persuasion insufficiently studied. To address this gap, we introduce LoFa (Logical Fallacy), a comprehensive benchmark for evaluating LLM robustness against fallacies. LoFa is constructed through a multi-agent pipeline that pairs factual questions with fallacious arguments, and is accompanied by a multi-round debate framework for assessing model resilience under sustained adversarial persuasion. To disentangle fallacy robustness from a model's inherent knowledge limitations, we further propose Logical Fallacy Resistance at k (LFR@k), a metric that quantifies resistance to fallacious attacks. Experiments show that LLMs exhibit varying levels of robustness across different fallacy types, revealing distinct vulnerability profiles among models.

Generative AI has emerged as a significant cybersecurity threat, with several recent attack campaigns leveraging LLMs to generate code for malicious purposes via scripting languages such as PowerShell. Consequently, for cybersecurity analysts, it is imperative to investigate the offensive capabilities of AI code generators. In this paper, we propose an experimental framework to assess LLM-generated PowerShell malware, which comprises a novel sandbox approach for dynamic analysis of AI-generated malware. Furthermore, we present a novel, manually curated dataset of real-world PowerShell malware, annotated in natural language to assist the training and evaluation of LLMs. Finally, this study evaluates permissive, open-weight LLMs adapted to PowerShell malware generation. Our results reveal a high degree of similarity between real malware and LLM-generated ones in terms of triggered OS malicious events, with a median Jaccard index of 84.5% and 48.4% of instances achieving complete overlap.

An unreliable language model can be made to produce reliable physical designs if the authority to assert is moved out of the model: the model proposes, and a deterministic engine alone certifies, returning certified, impossible, or unknown. We introduce Physics-Anchored Certification (PHACT), a propose-certify loop spanning five scientific domains, and identify what makes such a certificate trustworthy. A checker that accepts a model-supplied value can be forged; deriving the certified quantity from fixed inputs instead makes forgery impossible by construction. Across eighty adversarial trials spanning two models, two decoding temperatures, and a deliberately faulted engine, this contract produced zero false certifications.

In real-world applications, guardrails are often expected to identify unsafe user-model interactions according to application-specific safety policies, rather than relying on predefined risk taxonomies. In this work, we study this setting under the paradigm of in-context policy guardrailing, where guardrails predict safety violations based on policy specifications provided in context. To systematically evaluate this capability, we introduce SafePyramid, a safety benchmark comprising 1,000 multi-turn conversations across 10 domains and 3,000 corresponding application-specific policies, which together contain 61,699 distinct natural-language rules. SafePyramid organizes the evaluation into three difficulty levels: L0 evaluates individual-rule understanding, L1 evaluates reasoning over rule dependencies, and L2 evaluates adaptation of full novel policy frameworks defined in context. To ensure benchmark quality, we employ a rigorous multi-stage pipeline to construct and validate the benchmark. Using SafePyramid, we evaluate 10 frontier LLMs and 5 policy-configurable guardrails and find that in-context policy guardrailing remains highly challenging: even the best-performing model, GPT-5.5, exactly identifies the full set of violated rules in only 54.0%, 35.3%, and 12.9% cases on L0, L1, and L2, respectively. These results highlight the limitations of current guardrails and call for stronger in-context policy guardrails that can reliably execute policies, resolve rule dependencies, and adapt to novel policy frameworks.

How can we evaluate whether frontier AI systems recognize child-safety risks before they escalate into explicit harm? Existing child safety evaluations focus on child sexual abuse material, yet many child-safety failures begin earlier: in model assistance that helps adults manipulate, impersonate, profile, or isolate minors, and in model responses that deepen children's emotional dependence on AI systems rather than redirecting them toward human support. We introduce CAREBench (Child AI Risk Evaluation), a benchmark to assess such upstream child-safety risks in language models. CAREBench contains 500 prompts spanning twelve risk categories, including grooming and relationship engineering, deception and impersonation, surveillance and privacy, sextortion and sexual abuse, AI anthropomorphization, emotional dependency, and mental illness sensitivity. Developed with response annotations from parents and clinicians, the benchmark excludes explicit abuse material and imagery; instead, it evaluates whether models recognize, refuse, de-escalate, or redirect risky interactions before harm becomes overt. Evaluating seven frontier models on our benchmark, we find failure rates ranging from 2% to 58%, with failure patterns that vary across risk categories. CAREBench provides a responsibly scoped evaluation for LLM developers to identify and close gaps in child safety policies.

Rare events govern the safety profile of modern AI systems, yet their probabilities are extremely difficult to estimate: direct Monte Carlo requires prohibitive sample budgets. Subset Simulation (SS) addresses this by decomposing a rare-event probability into moderate conditional probabilities over nested intermediate events. However, classical SS requires a handcrafted scalar performance function whose sublevel sets define those events, demanding detailed knowledge of the failure geometry and limiting transfer to new domains. We propose SCARCE (Scalable Cascade Analysis for Rare-event Characterisation via Embeddings), which replaces the performance function with learned latent representations and geometric rulers that score proximity to failure regions. Adaptive thresholding constructs nested intermediate events directly from data. We formalise SCARCE through a non-negative supermartingale, yielding a high-probability upper envelope that remains valid under early stopping. On MNIST misclassification, where dense Monte Carlo provides ground truth, SCARCE achieves approximately 400--500 times lower mean absolute error than grid-searched traditional SS while eliminating systematic over-counting. We then study PAIR-style LLM jailbreaks under a fleet-level threat model with adversarial fraction $η$. On Llama-Guard-3-8B hidden states, a PCA-based ruler attains 2.6% mean relative error for $η\geq 10^{-3}$ against finite-sample references whose average bootstrap relative half-width is 27.9%, and transfers to a GCG-style corpus with 2.93% relative error after recalibration. A directional criterion $\mathrm{KL}(p_{\mathrm{good}}\,\|\,p_{\mathrm{bad}})$ ranks rulers consistently with estimation error (Spearman $ρ=0.83$).

Modern LLM deployments often combine quantization with higher sampling temperatures to reduce cost, latency, or repetition, yet safety evaluations usually treat these as fixed implementation details. We test whether models that are safe at FP16 with greedy decoding remain safe after quantization and stochastic sampling, or whether the two factors amplify each other. We evaluate 8 instruction-tuned models from five families across 3 precisions and 6 temperatures, covering 144 configurations on 7 harmfulness benchmarks and generating about 2.0 million responses, which are scored by a six-judge safety ensemble. Contrary to concerns that low-bit deployment erodes alignment, we find that standard quantization is approximately safety-neutral: for 7 of 8 models, AWQ INT4 keeps attack success within about 1.6 percentage points of FP16 or lowers it, with clear degradation only for SmolLM3-3B (34.5% to 44.1%). However, the larger risk comes from sampling: higher temperatures sharply increase decision instability, with DFR reaching 41.9% at T = 1.0, even when average ASR changes only modestly. The two factors do not compound: our Compound Degradation Index remains sub-additive (-0.071 to +0.018), indicating that quantization partially offsets rather than amplifies temperature-induced degradation. Finally, a per-benchmark breakdown shows that single-benchmark evaluation badly understates risk: several models scoring 0% on AdvBench exceed 80% on ManyHarm. Standard INT4/INT8 quantization can therefore be reasonable for well-aligned models, but safety claims should report multi-sample stability across multiple benchmarks rather than rely on a single benchmark at greedy decoding.

LLM-based assistants transmit user queries verbatim to third-party API endpoints that lie outside the user's audit or control. When those queries contain personally identifiable information (PII), the data persists on remote infrastructure subject to breach, subpoena, or policy change. Placeholder redaction (the prevailing mitigation) suppresses PII at the cost of semantic coherence, producing structurally degraded queries and correspondingly degraded responses. We present SurrogateShield, a client-side proxy that substitutes detected PII with locally generated, type-consistent surrogate values prior to transmission and restores originals in the response. No real PII crosses the network boundary. Detection runs through a three-stage cascade (PatternScan, EntityTrace, and ContextGuard) covering 22 PII types and quasi-identifier combinations grounded in Sweeney's k-anonymity framework. Surrogate-to-original mappings are sealed in an AES-256-GCM encrypted per-conversation ShadowMap that never leaves the device. Evaluations on a 1,124-query corpus demonstrate that the cascade reliably detects PII, achieving an overall F1 score of 98.87%. Surrogate substitution substantially outperforms placeholder redaction in semantic utility, yielding a 13.26 pp improvement in BERTScore (roberta-large), from 81.59% to 94.85%. Within this corpus, the local pipeline restricted real PII transmission across all tested query types; in a 100-query adversarial trial, a prompted LLM adversary recovered no original values from surrogate-substituted messages.

Large language models (LLMs) increasingly mediate strategic interactions through natural language, making semantic control a critical element of communication and deception. This paper develops a semantic signaling game in which a sender selects a semantic control, an LLM generates a stochastic message, and a receiver evaluates the message using an awareness-dependent scoring mechanism. Receiver awareness is modeled as a type that determines which linguistic features are perceived and used for inference, providing a formal model of systematic blindness. The framework connects prompt-based control, statistical detection, and game-theoretic equilibrium analysis. Gaussian approximations of aggregate message scores enable likelihood-ratio decision rules, while Perfect Bayesian Nash equilibria characterize strategic behavior. The paper further develops mechanism-design approaches that reshape receiver awareness, penalize deceptive semantic controls, and modify receiver populations to induce benign pooling equilibria. Numerical experiments validate the Gaussian approximation, quantify awareness-ordering effects, analyze mindset dynamics under adaptive adversaries, and demonstrate how awareness shaping and guardrail costs reduce successful phishing attacks. The proposed framework provides a principled foundation for analyzing strategic language-mediated interactions in agentic AI systems and offers new tools for the design of robust and secure human-AI communication.

Large language models (LLMs) deployed for structured generation (NER, JSON extraction, QA, and classification) lack formal reliability guarantees, and standard heuristic abstention policies miss user-specified risk targets by 7.5--12.5%. We characterize when conformal risk control (CRC) can certify structured LLM outputs and when it provably cannot. First, we prove an impossibility result: when the base risk (μ> α), any distribution-free method must abstain on at least ((μ-α)/(1-α)) examples, yielding a closed-form feasibility test: one can check whether CRC will work before running it. Second, we analyze a certification hierarchy across Hoeffding, empirical Bernstein, and a betting-based e-CRC bound, with strict gains in low-variance/large-sample regimes: the Hoeffding-to-Bernstein step delivers the largest gain (+37% certified configurations), while e-CRC adds value when calibration data is scarce (10% certification at 20% data versus 0% for Hoeffding). Third, we validate adaptive conformal inference (ACI) under cross-dataset shift, reducing risk-target violations from 71% to 21%, with residual failures concentrated exactly where the impossibility bound predicts. Across six open-weight models (3B--72B parameters), eight datasets, four tasks, and six nonconformity scores, hard NER/QA/CLS configurations are uncertifiable at (α= 0.10); relaxing to (α= 0.30--0.40) unlocks practical certification (47% NER, 40% QA, 60% CLS). The framework gives a three-step deployment recipe: check feasibility, select the bound and score, then mitigate shift.

Cybersecurity is a real-life test-bed for many machine learning problems at once, especially when considering modern strides in using Large Language Models (LLMs) to automate processes as ``agents.'' Cybersecurity workflows require orchestrating hundreds of standard and bespoke tools through various formats. The scale of cybersecurity data is enormous; for example, a single malware sample can be viewed as a sequence of billions of tokens. The cost of labeling any file by experts is enormous and labor-intensive, in part because an adversary (possibly a well-funded nation state actor) is attempting to subvert your detection methods. Even skilled experts may disagree on the correct label, creating ambiguity in what constitutes ground truth. When deployed, models must run quickly on billions of items a day, where low-latency is critical for operational success, in a continuously changing environment. In addition, explainability is not optional: analysts demand clear reasoning for model decisions to cope with the large number of false-positive alerts they face daily, and to quickly develop remediation and understand how something went wrong. In short, the amount of complexity cybersecurity is greater than that of natural language and computer vision, and thus we posit that cybersecurity is the better test-case for general AI progress than other, well-studied fields.

AI systems increasingly exhibit behavior that differs systematically between evaluation and deployment contexts. Alignment faking, sandbagging, benchmark gaming, deceptive scheming, specification gaming, and trojans have each been documented separately, with each line of work characterizing one facet of what we argue is a single structural mechanism. We propose that this common mechanism is a defeat device, an engineering and regulatory concept long established in vehicle-emissions law and brought to broad public attention by the 2015 Volkswagen emissions case. A defeat device in an AI system has three necessary elements: a discriminator that detects evaluation context, a concealed swap that conditions behavior on detection, and a gap between eval-distribution and deployment-distribution performance on the stated evaluation criterion. We formalize this triadic test as a behavioral definition, organize documented cases along three taxonomic axes (origin, trigger, swap mechanism), propose Trigger-Axis-Aware Differential Probing (TADP) as a forensic detection protocol, and advance the claim that defeat devices can naturally emerge in current frontier AI systems without any operator engineering. We characterize naturally-emerging defeat devices as potentially one of the harmful emerging phenomena that AI safety practice should monitor and test for systematically. Implications for evaluation methodology, post-training pipeline design, interpretability research priorities, and AI governance follow.

Fine-tuning a large language model is a ubiquitous method for enhancing its capability on a specific downstream task. However, prior work has shown that this increase in capability comes with a cost: it can increase a model's tendency to respond to unsafe adversarial prompts, even when fine-tuning with non-adversarial data. We present the first comprehensive empirical study of this phenomenon in multilingual settings by fine-tuning Llama-3.2, Qwen3, and Gemma-3 models using benign data translated across nine languages. We find that safety outcomes are highly sensitive to both the choice of fine-tuning language and the evaluation language, with adversarial compliance rates increasing four-fold in some settings. Multilingual safety drift is decoupled from general capability metrics, and occurs heterogeneously across languages and models. Fine-tuning in non-English languages often induces smaller internal representational drifts than English, but these shifts lead models to default to either exaggerated compliance or refusal. As such, assessing fine-tuning impacts solely in English provides inadequate assurance for deployment. To facilitate further research into these cross-lingual safety blind spots, we release the Multilingual-Benign-Tune dataset and the SORRY-Bench-Multilingual evaluation suite.

Agent-based AI has enabled the automation of tasks by exposing application tools and resources to large language models (LLMs). However, to improve scope and accuracy, agents are often given access rights that exceed those of ordinary users, introducing significant security risks. AI is routinely integrated into applications with a disregard to security, risking data exposure and breaching regulations. This paper applies the AI Trust, Risk, and Security Management (TRiSM) framework to a medical report-generation application to demonstrate how an insecure agent workflow can be transformed into security-conscious agentic workflow. Both workflows were evaluated across five LLMs (Claude Haiku 4.5, GPT-4.1-nano, GPT-4.1-mini, GPT-5.4-mini, and Gemini 2.5 Flash) on two report types, totalling 800 generations and 500 attack scenarios including RAG poisoning, data-field injection, and client-side network injection. The TRiSM-guided agentic workflow reduced mean attack success rates from 31% to 10% for RAG poisoning and from 42% to 25% for data-field injection, while eliminating the network injection vector entirely through server-side prompt construction. Furthermore, report accuracy increased by 14 percentage points (72.5% to 86.5%) with the agentic workflow, demonstrating a secure design which provides more reliable outputs. This paper contributes to knowledge by demonstrating least-privilege, defence in depth agentic workflows improving security and accuracy, while also highlighting model choice is a necessary architectural consideration.

Jailbreak attacks bypass LLM safety alignment, yet their mechanisms remain poorly understood. We provide evidence that attacks do not comprehensively eliminate safety features, but instead selectively suppress specific attention heads. We identify two functionally differentiated types: Adversarially Compromised Heads (ACHs) concentrated in early layers, which are suppressed under attacks, and Safety-Aligned Heads (SAHs) in mid-layers, which maintain robust activations even when attacks succeed. Ablation studies support the causal role of ACHs and the contribution of SAHs to robust activations: suppressing a small number of ACHs is sufficient to induce jailbreak-like behavior on normally refused inputs, while removing SAHs substantially weakens mid-layer safety activations. Token-level attribution further shows that ACH suppression is driven specifically by attack-template tokens, providing a mechanistic account of why attacks can bypass refusal decisions through ACH suppression while leaving internal safety signals sustained by SAHs -- a phenomenon we term Robust Harmful Features. To validate the practical significance of this robustness, we show that simply reading these persistent activations -- without any training -- yields competitive aggregate detection performance with strong adversarial robustness.

As large language models are increasingly deployed in real-world systems, safety failures can still lead to harmful outputs and dangerous misuse. We argue that the essence of safety is adversarial: many failures arise not from natural inputs alone, but from strategic attempts to evade model policies and safeguards. However, existing general-purpose model development largely overlook this adversarial nature, and often remain insufficient for realistic safety scenarios involving planning, tool use, and multi-step reasoning, causing measured safety performance to overestimate real deployment robustness. To address this gap, we present Yuvion LLM, a large language model built for adversarially robust content safety and broader AI safety. Yuvion LLM treats adversarial robustness and agentic capability as first-class objectives. Its pipeline combines adversarially aware data construction, knowledge-enhanced continued pretraining, and policy-grounded multi-task safety post-training, including risk-aware supervised fine-tuning and reinforcement learning-based policy optimization, together with safety-aware agentic reinforcement learning for tool use and multi-step reasoning in complex safety scenarios. We further introduce the Yuvion LLM RiskEval (YLRE), a collection of 93 benchmarks across four evaluation categories, covering diverse open and internal evaluations with a focus on safety, adversarial robustness, and real-world capability requirements. Across these evaluations, Yuvion LLM demonstrates clear advantages on safety-focused benchmarks and particularly strong robustness under adversarial conditions, while maintaining solid overall capability. Notably, Yuvion-8B outperforms most state-of-the-art baselines, including substantially larger models such as GPT-5.4 and Qwen3-MAX, on several safety tasks.

We argue that safety classifiers should model user intent as an explicit signal between the prompt and the final label. To study this, we introduce AIMS, a human-annotated dataset of 1,724 difficult safety prompts, each paired with an intent description and harm label. We use AIMS to evaluate intent-aware training across supervised fine-tuning, preference learning, reasoning distillation, and reinforcement learning. Despite its size, AIMS enables competitive safety classifiers across training regimes: DPO from model-generated intent errors improves over SFT, and intent-conditioned distillation outperforms reasoning-only distillation in most teacher-student pairs. Most notably, directly rewarding intent faithfulness with GRPO yields the strongest average performance across five external safety benchmarks, while our intent-aware models form the inference latency-F1 Pareto frontier. These results show that faithful intent modeling is a compact, high-quality supervision signal for more robust safety classifiers.

We present a novel approach for applying Large Language Models (LLMs) to threat assessment in the context of foreign peacekeeping missions. Building on the PINPOINT project and its use case, the EU Monitoring Mission in Georgia, we combine an interdisciplinary risk-model with OSINT-based media collection and LLM-supported threat extraction. The proposed workflow maps media contents to mission-relevant threats, extracts structured information and applies several additional LLM-based processing steps to improve relevance and grounding. An evaluation of threats extracted from media documents shows high agreement between automatically generated results and human judgment for core aspects such as threat and mission relevance. These results indicate that LLMs provide a promising approach to support analysts in the context of peacekeeping missions.

Speech-capable models are increasingly deployed in real-world applications across languages. Yet their safety and fairness beyond English settings and under naturalistic conditions remain understudied. We survey safety reporting practices across state-of-the-art speech model releases, finding that only 8% document any multilingual analysis. To address this gap, we introduce RedVox, a multilingual safety and fairness benchmark for audio and speech built on real voices, covering unsafe and unfair stereotypical requests across five languages (English, French, Italian, Spanish, and German). Evaluating eight state-of-the-art models, we find that vulnerabilities persist even under non-adversarial conditions, worsen in non-English languages, and are amplified when the request comes from a spoken input. Finally, by surveying the participants who contributed to RedVox, we document the unique personal and privacy challenges of collecting speech data with human participants, pointing to broader sociotechnical challenges in naturalistic speech safety research.

In order to screen a prompt or a response, the recent guardrail methods generate a chain-of-thought (CoT) before they issue a verdict. This design follows a common belief that step-by-step reasoning improves a decision. However, CoT also makes the guard heavy and slow, because the model must generate many tokens before it decides. This may not match how guardrails are actually deployed. A guardrail sometimes should not be heavy and slow, and it often runs on-device, for example on an embodied robot. In this paper, we pose a question whether a safety guardrail really needs to reason. To answer this question, we train a lightweight bidirectional encoder and a reasoning guard on the same corpus, and we then remove only the reasoning while we keep everything else fixed. With this controlled same-base comparison, we show that the chain does not improve moderation accuracy. We name the resulting guard LeanGuard. A 395M label-only encoder reaches an average F1 of 82.90 $\pm$ 0.26 over public benchmarks. It matches a reasoning guard that is built on a much larger decoder, while it uses only a single forward pass over an input of at most 512 tokens. This is about a ~100x reduction in inference compute. We further show that this label-only encoder stays robust under training-label noise and retains far more recall at a strict false-positive rate than the reasoning guard, so a heavier reasoning guard is not the more robust choice either. Our finding suggests that the current guardrail benchmarks may not be hard enough to reward reasoning, and that the necessity of CoT for moderation is still not proven. We release all source codes and models including LeanGuard at https://github.com/ndb796/LeanGuard.

Adversarial evaluation of AI systems has matured along four largely disconnected tracks: diffusion-based attacks on text and large language models (LLMs), diffusion-based attacks on image classifiers, jailbreak pipelines against vision-language models, and diffusion-based input purification defenses. Each has developed its own vocabulary, threat models, and benchmarks, with denoising diffusion models emerging as a shared generative mechanism whose recipes are now actively ported between communities. This survey performs an information-fusion exercise at the meta-research level: we integrate these four tracks into a single conceptual framework with a unified taxonomy, evaluation criteria, and research agenda, focusing on the LLM-side slice. We catalog fifty published papers across four scope areas (text/LLM, image classifier, vision-language model, defense), plus four diffusion-LLM-as-victim entries and ten non-diffusion baselines against which any new attack must be compared. We propose a six-class taxonomy of diffusion roles in adversarial pipelines, augmented by a threat-model axis recording attacker knowledge, query budget, and target accessibility, and apply a five-dimension framework (attack success rate, transferability, query budget, perplexity, defense-evasion) uniformly across modalities. The review adopts a dual attacker-defender perspective: alongside the attack catalog we cover four diffusion-based defenses that form the natural evaluation backdrop for new attacks. Our critical analysis identifies five recurring weaknesses of the current LLM-side literature, and we close with a research agenda of open questions and concrete experimental designs. The companion catalog and spreadsheet are released with the paper. We are explicit that this is a narrative review with quality assessment, not a PRISMA-compliant systematic review, and discuss the implications for replication.

Training-time data poisoning during fine-tuning poses a significant threat to large language models (LLMs) deployed for abstractive text summarization, where small task-specific datasets exert disproportionate influence on model behavior. In this setting, adversaries manipulate fine-tuning data to induce persistent summarization failures, such as biased or harmful summaries, while preserving standard evaluation metrics. We present a unified post-hoc defense framework for detecting and remediating fine-tuning-stage poisoning in summarization models across the machine learning supply chain. Our experiments show that in white-box settings, poisoned document-summary pairs exhibit abnormally high training influence, enabling detection via influence-function analysis with semantic consistency checks. In black-box settings, poisoned models display two to three times greater sensitivity to semantics-preserving perturbations, enabling behavioral auditing without training data access. Beyond existing poisoning formulations, we introduce novel attacks targeting factual distortion and representational bias, showing that poisoning alters summarization behavior without triggering conventional alarms. Across nine architectures and six benchmark datasets under adaptive attacks, our defenses achieve 85-92% detection precision, while gradient-ascent unlearning restores up to 96% of original behavior with minimal utility loss (less than 0.6% ROUGE degradation). These results indicate that fine-tuning-time poisoning leaves persistent structural artifacts, enabling practical detection and post-deployment recovery without full retraining.

With the widespread adoption of large language models (LLMs) in chatbots and everyday applications, companies increasingly need guardrails that are effective while remaining low-cost and low-latency. Safety evaluation of LLM outputs has generally relied on LLM-based judges, which can be effective but are often slow and expensive to deploy at scale. In this paper, we evaluate whether fine-tuned modern encoder classifiers from the ModernBERT family, including ModernBERT and Ettin, can reliably identify harmful LLM outputs in user-model conversations without substantial performance loss relative to LLM-based judges. We benchmark these encoder classifiers against rule-based prefix matching, fine-tuned LLM classifiers, and LLM judges using a range of judge-prompting strategies across open-source adversarial datasets. The LLM judges include evaluation methodologies from StrongReject, ShieldGemma, JailbreakBench, AILuminate, SorryBench, and a Claude-as-a-judge setup, as well as fine-tuned safety classifiers such as LlamaGuard 3 and LlamaGuard 4. The encoder classifiers are fine-tuned on judge-labeled data using a majority-voting label strategy and are then evaluated on a gold-standard holdout dataset to assess their performance relative to LLM judges. We report absolute performance using F1 score, false negative rate, and precision-recall metrics. We also break down results by attack technique, including single-turn prompting, decomposition, escalation, and context manipulation, to identify where encoder classifiers align with or diverge from LLM-based judges. Our findings provide guidance on when encoder classifiers can serve as cost- and latency-efficient alternatives to LLM-based safety evaluation.

Safety evaluation of large language models (LLMs) is commonly performed by querying models with unsafe or jailbreak prompts and judging whether their outputs violate a safety policy. Although useful, output-level evaluation is expensive, sensitive to judge choice, and easily tied to fixed question banks. We propose SafeVec, a white-box evaluation procedure that measures safety from internal representations rather than generated answers. SafeVec first extracts layer-wise refusal directions from a safety-aligned reference model, then selects stable layer windows where safe and unsafe behaviors are separable, and finally scores a target model by measuring whether its hidden states align with these refusal directions under unsafe and jailbreak prompts. The resulting metric, RAS (Refusal Alignment Score), maps representation-level refusal alignment to a calibrated 0-100 safety score. Across Llama, Gemma, and Qwen model families, RAS separates aligned models from uncensored and abliterated variants, tracks output-level attack success rate, and is substantially faster than judge-based evaluation. These results suggest that refusal alignment provides a compact and efficient signal for white-box LLM safety evaluation.

Retrieval-Augmented Generation (RAG) systems are vulnerable to corpus poisoning attacks that manipulate model outputs through malicious retrieved documents. Existing detection methods typically rely on auxiliary classifiers or additional LLM-based verification, introducing substantial computational overhead. We present TRACE, a lightweight detection framework that identifies poisoning attacks by tracing answer-related tokens through token influence attribution. TRACE first discovers recurrent high-influence keywords across retrieved documents and then performs a secondary verification to confirm their influence on model predictions. Experiments on three QA benchmarks and six LLMs demonstrate strong detection performance while simultaneously uncovering attacker-specified target answers.

This paper presents a novel approach to perform semi-automated BSI IT-Grundschutz certification using a MultiLarge Language Model system (MLS) with Hybrid RetrievalAugmented Generation (HybridRAG). Facing the challenges of the Network and Information Security Directive 2 (NIS2) directive, a shortage of specialists, and high implementation costs, our MLS architecture aims to increase efficiency, reduce costs, and support certifiers in maintaining the quality of security concepts while meeting the increased demand for certifications of newly affected companies. The system combines Large Language Models (LLMs) and Knowledge Graphs (KGs) to support different phases of the certification process, including protection needs assessment, modeling, IT-Grundschutz check, measure consolidation, and subsequent realization. Our architecture addresses the growing demand for security concepts and offers an approach to handle the digital security challenges introduced by NIS2.

Retrieval-Augmented Generation (RAG) has emerged as a dominant paradigm for enhancing large language models with external knowledge. By coupling retrieval mechanisms with generative models, RAG systems improve factual grounding and adaptability across domains. However, integrating retrieval pipelines introduces new security and privacy risks that extend beyond conventional language modeling threats. Sensitive information may be exposed through retrieval indices, query logs, context construction, or federated updates, while adversarial manipulation of knowledge bases can undermine trust in generated outputs. This survey provides a comprehensive examination of privacy and security challenges across RAG systems deployed in centralized, on-device (Micro-RAG), federated, and hybrid paradigms. We present a unified taxonomy of threat surfaces spanning the retrieval, context construction, and generation stages and systematically analyze attack classes, including membership inference, index inference, poisoning, gradient leakage, and collusion. We further review architectural, algorithmic, and cryptographic defenses, highlighting privacy-utility trade-offs and deployment considerations. Finally, we outline open research challenges toward building trustworthy, secure, and resilient RAG systems for real-world applications.

Large language models (LLMs) have demonstrated remarkable performance across natural language processing tasks, yet their deployment in high-stakes applications raises critical concerns regarding reliability, safety, and trustworthiness. In this paper, we present a red teaming framework that systematically uncovers vulnerabilities in LLM outputs. Our approach employs a novel multi-role architecture comprising target, attacker, and jury models. The attackers generate increasingly effective adversarial prompts while the jury rigorously evaluates response accuracy and consistency across tasks. In a case study, our strategy proved particularly effective at exposing unfaithfulness in LLM responses. Exploitative adversarial prompts increased the attack success rate by up to 7.9% in question-answering tasks, revealing weaknesses in reliability. The approach identifies how structural constraints in summarization can shape vulnerability patterns, with format limitations yielding measurable gains in faithfulness, and shows that architectural design choices typically outweigh parameter scaling in determining model safety. The framework's key strength is its adaptability across evaluation tasks, from English question-answering to Arabic summarization, enabling comprehensive comparison of model vulnerabilities. While it excels at comparing cross-model and cross-linguistic vulnerabilities, it faces challenges in fully automating adversarial prompt generation across languages. Our experiments also reveal limitations in detecting subtle forms of unfaithfulness that do not manifest as explicit factual contradictions, particularly across linguistic contexts. Overall, this architecture provides both actionable insights into current LLM vulnerabilities and a scalable methodology for ongoing safety evaluation as models evolve.

Safety alignment of large language models (LLMs) typically depends on high-quality supervision data, such as safe demonstrations or preference pairs. However, in real-world deployment, emerging safety requirements are often specified as natural-language policies, while corresponding supervision data may be costly, delayed, or unavailable. This creates a mismatch between rapidly evolving safety policies and conventional data-driven alignment methods. To address this, we propose PolicyAlign, a simple yet effective framework for directly aligning LLMs with safety policies. Given a safety policy, PolicyAlign first synthesizes policy-violating instructions and then performs on-policy self-distillation to internalize policy-guided behavior. To improve training stability and data efficiency, we further introduce Policy-Sensitive Filtering, which selects instructions where the policy induces the largest behavioral shift. Experiments across multiple models show that PolicyAlign consistently improves safety while maintaining low over-refusal and preserving general capabilities. PolicyAlign also generalizes to medical, legal, and financial safety scenarios, highlighting its potential as a scalable and maintainable approach to policy-based LLM safety alignment. The code is released at https://github.com/Qwen-Applications/PolicyAlign.

Large language models (LLMs) are increasingly deployed across languages, but their safety behavior remains uneven across linguistic and cultural contexts. This survey synthesizes work on toxicity detection and detoxification for multilingual LLMs. We first catalogue threat models that exploit language choice, translation pivots, code-switching, orthographic variation, multi-turn interaction, and post-deployment fine-tuning to weaken safety alignment. We then organize task formulations (toxic-to-neutral rewriting, toxicity classification, and toxic-generation evaluation), multilingual detection approaches (cross-lingual encoders, translation pipelines, representation-level probes, and LLM-based detectors), and mitigation strategies spanning data filtering, supervised and preference-based tuning, decoding-time steering, representation editing, and multilingual guardrails. Across these areas, we identify persistent challenges: uneven language coverage, culturally contingent definitions of harm, fragmented evaluation protocols, and the risk that detoxification suppresses legitimate dialectal or identity-related expression.

The increasing use of AI systems for code generation raises a central security question: what can today's models and coding agents actually do to produce secure code, where do they still fail, and what would move the field forward? Existing work has explored prompting, fine-tuning, reinforcement learning, and agentic workflows for secure code generation, but the field still lacks a systematic understanding of how these techniques improve security and why substantial failures persist. In this SoK, we systematize the progress, pitfalls, and paths forward for AI secure code generation. We introduce a three-level framework that measures models' natural-language understanding of secure coding principles, their code-level actuation of those principles during generation, and the knowledge--actuation gaps between the two. We instantiate this framework across models and coding agents on benchmarks covering both isolated function-level security and full web-application security. Our results show that secure-coding-principle understanding is a statistically strong predictor of code-level outcomes, including functional correctness, security, and joint functional-security correctness. Yet substantial knowledge--actuation gaps remain: models can recognize relevant security principles but still fail to translate them into secure and functional code. These findings offer a principle-centered account of where AI secure code generation stands today and identify concrete paths forward through principle-guided generation, evaluation, benchmarking, and agentic workflows.

Jailbreak attacks reveal a persistent weakness in aligned Large Language Models: carefully crafted prompts can elicit policy-violating responses despite safety training. While most defenses operate at the prompt or output level, it remains unclear how harmful intent is encoded within the model's internal representations. We investigate this question by analyzing token-level predictive entropy trajectories across layers of a frozen LLM using the logit lens. We find that static aggregate statistics of prompt-level entropy (e.g., mean, variance) carry little discriminative signal, whereas features capturing how entropy evolves across token positions, such as monotonic rank-based trend scores, are substantially more informative. Importantly, this signal is not uniform across model depth: it is concentrated in intermediate layers and degrades at the final layer, indicating that jailbreak-relevant structure is most pronounced in mid-network representations rather than at the output head. Across multiple models (Llama, Qwen, Gemma) and adversarial benchmarks, these entropy dynamics provide architecture-consistent separation without additional training. Together, our findings show that jailbreak behavior is reflected in structured intermediate uncertainty dynamics, clarifying both which entropy-derived features encode harmful intent and where in the network that signal is most pronounced.

Deployed approaches for AI text detection often rely on training-time access to labeled datasets of both human-written and AI-generated text. This approach is vulnerable to three types of distribution shifts that occur continually post-deployment, and for which labeled data is often unavailable: adversarial humanization, new LLMs being released, and temporal drift in human writing. Simultaneously, existing approaches do not leverage a key signal of LLM usage: inference-time homogeneity. We propose a test-time adaptation (TTA) approach, using semi-supervised learning, that adapts to distribution shifts by leveraging homogeneity among unlabeled samples observed at inference time. Empirically, we find that state-of-the-art supervised detectors systematically fail when they encounter distribution shifts in AI-generated and human writing, both adversarial and natural, while test-time adaptation with semi-supervised learning is largely robust; e.g., the commercial model Pangram detects just 24.1% of our adversarial AI-generated text, compared to 90.5% for our test-time approach. We establish that test-time adaptation is a promising framework for AI text detection in the wild. We publicly release our code (which includes code for model training, evaluation, and plots) at https://github.com/kkr36/llm_detection.

Speculative decoding accelerates inference by letting a draft model propose tokens for a target model to verify, raising a concrete safety question: at temperature zero, can draft-side behavior leak into safety-scored outputs? We answer with Typical-Acceptance Invariance Screen (TAIS), a behavioral-equivalence screen that pairs target-only and speculative outputs on the same safety battery and requires byte-identity evidence, TOST equivalence at +/-3pp, and per-task Cohen's h below a calibrated null cutoff of |h| < 0.1. Applied to a 16,783-sample confirmatory core plus 44,066 matched expansion samples (fp16/bf16 execution, canonical and DPO-adversarial drafts, GPTQ-4bit drafts, two seeds, and four safety benchmarks), the tested temperature-zero vLLM stacks show no detectable safety divergence under TAIS. The largest absolute Cohen's h on matched target-only versus speculative refusal is 0.024, roughly an order of magnitude below the conventional trivial-effect floor; 25 of 27 per-task TOST contrasts pass at the +/-3pp margin (the two non-pass contrasts are capability-domain Wald-CI edge cases at identical ceiling rates, not genuine non-equivalence); the DPO-adversarial draft produces byte-identical output to the canonical draft across 4,006 samples; and bf16 changes 36%-53% of output bytes without moving any per-task safety rate outside equivalence. A separate 4,006-sample 70B production-scale probe, which lacks a matched 70B target-only arm and is therefore not counted as a TAIS pass, produces AdvBench refusal 0.839 over 700 AdvBench completions with 95% Wilson CI [0.809, 0.864]. We make no claim about sampling temperatures, untested frameworks, untested model families, or tree-speculation variants such as EAGLE and Medusa.

General-purpose models often struggle to reliably identify and understand real-world multimodal risks, largely due to the inherent multimodal adversarial nature of content and AI safety. We present Yuvion VL, a family of multimodal large language models purpose-built for content and AI safety, with both instruction-tuned and reasoning-oriented variants. Yuvion VL addresses this gap by treating safety as an inherently adversarial and multimodal problem and designing the entire pipeline around adversarial robustness. For data construction, we develop an automated pipeline integrating adversarial-aware data synthesis with multi-stage quality control, producing large-scale, high-quality multimodal samples augmented with domain knowledge and reasoning annotations. For training, we adopt a three-stage pipeline that includes continued pretraining for risk-concept cross-modal alignment, instruct post-training for production-grade safety tasks, and reasoning post-training for enhanced interpretability and performance in complex tasks. We further introduce Confuse-then-Contrast Fine-Tuning, a contrastive framework that mines model-specific confusions and constructs multi-image contrastive groups to enforce explicit discrimination of fine-grained visual-semantic elements, enabling the model to distinguish between visually similar cases with different safety implications in adversarial safety tasks. To support rigorous evaluation, we further introduce Yuvion VL RiskEval (YVRE), a collection of benchmarks covering diverse open and internal evaluations, with a focus on content and AI safety, adversarial robustness, and real-world capability requirements. Experiments show that Yuvion VL-32B achieves industry-leading safety performance, surpassing comparably sized open-source models and best closed-source commercial models, while maintaining comparable general capabilities.

Scaling adversarial evaluation of large language models requires both a method for generating hard inputs and a reliable way to confirm that resulting failures are real. We present AdversaBench, an end-to-end red-teaming pipeline that mutates seed prompts with five structured operators, queries a target model, and confirms failures through a three-judge panel with a meta-judge tiebreaker. We report experiments on 45 seeds across three categories: reasoning, instruction-following, and tool use. Every seed produced a confirmed failure. Four findings stand out. First, operator effectiveness varies sharply by category: inject_distractor scores 0.00 mean reward on instruction-following seeds but 0.80-0.83 on reasoning and tool-use. Second, binary failure rate hides difficulty: instruction-following seeds required 2.4 attacker iterations on average versus 1.1 for other categories, a gap visible in survival curves. Third, pairwise judge agreement of 80-87% coexists with near-zero Cohen's kappa due to label skew; category-level disagreement rates are more informative. Fourth, adversarial prompts generated against Llama 3.1 8B transfer zero-shot to Llama 3.3 70B, suggesting the mutations exploit general behavioral patterns rather than model-specific weaknesses. Code, dataset, and analysis scripts are available at https://github.com/khanak0509/AdversaBench .

Object interaction tasks have been a focus of advances in imitation learning. End-to-end methods, dominated by diffusion and flow-based variants have shown leaps in performance while sacrificing interpretability. Object-centric and pose-informed variants have had a role in learning from demonstration in manipulation tasks. In this paper, we revisit a few modern imitation learning benchmarks for object interactions, with the aim of composing a framework that repurposes principled theories of manipulation, preserving both performance and interpretability. For image observations, lightweight training is proposed for model-free pose estimation of the target object, using self-supervision over the demonstration data available for imitation learning. This information is then used to inform a manipulation mode-aware retrieval of a demonstration, a mode-aware transformation, a replan step that connects to the retrieval point while preserving mode constraints, and finally rolling out the transformed demonstration. These compose four key steps of the proposed RE4 framework, evaluated over state-based and image-based benchmarks in Push-T and Robomimic. An adversarial benchmark that evaluates sparse data regions of image-based Push-T showcases the robustness, further bolstered by indications from low-data regime experiments. The current work shows promise in using simple interpretable building blocks to learn manipulation skills.