Safety Alignment

Large reasoning models (LRMs) achieve remarkable success on complex tasks but remain vulnerable to harmful prompts that induce unsafe outputs. Recent methods align LRMs using direct refusals or safety rationales, yet often focus on prompt patterns rather than intrinsic attack mechanisms. As a result, these pattern-centric alignments struggle to generalize across diverse jailbreaks, compromising adversarial robustness and reasoning utility. We propose AdvSafe, a dual-adversarial framework that enables LRMs to internalize unsafety knowledge by explicitly deconstructing adversarial mechanisms. This moves beyond pattern-dependent traces, fostering robust cognitive defense without compromising reasoning utility. Our pipeline operates via a two-phase adversarial game. First, in adversarial synthesis, an autonomous agent dynamically crafts deceptive jailbreak prompts, adapting its strategies to breach a strong teacher model. Second, in adversarial extraction, the breached teacher executes a cognitive counter-attack. For every successful jailbreak, the teacher unmasks the camouflage, explaining why the attack succeeds and how such prompts can be identified and mitigated. This dual-adversarial process yields a compact reasoning dataset capturing rich, generalizable unsafety knowledge. Student models trained on this dataset implicitly acquire safety alignment through intrinsic threat comprehension. Experiments show that with only 1K synthesized samples, AdvSafe-aligned LRMs achieve significantly stronger jailbreak robustness than existing baselines, with almost no utility degradation. Furthermore, AdvSafe improves robustness against out-of-distribution prompts, demonstrating that learning unsafety knowledge enables a superior robustness-utility trade-off and generalizes beyond seen attack patterns.

The deployment of autonomous robotic systems in chemistry laboratories is accelerating experimental workflows and providing the foundational data for AI-driven scientific discovery. However, despite the success of data-driven methods in acquiring dexterous skills, safety remains a primary barrier to their deployment in high-risk domains, such as early-stage materials chemistry experiments. Specifically, learning-based policies frequently struggle to distinguish between safe and unsafe actions, leading to overconfident extrapolation and potentially catastrophic failures. To mitigate these safety risks, we propose SAFE-CHEM, an uncertainty-aware framework designed for robust, learning-based robotic chemists. Our approach leverages an ensemble of recurrent neural network-based imitation learning policies to quantify epistemic uncertainty online through the variance of action predictions. By characterising the success-conditioned density of this variance using kernel density estimation, we introduce a hybrid control architecture that autonomously switches from the learned policy to a deterministic, rule-based backup controller when uncertainty exceeds a calibrated safety threshold. We evaluate SAFE-CHEM across three fundamental laboratory manipulation tasks, where our empirical results demonstrate that this hybrid strategy improves overall task success rates and reduces critical safety violations compared to traditional single-policy baselines. Finally, we demonstrate the practical viability of the framework through zero-shot sim-to-real transfer onto a physical Franka Production 3 robot manipulator.

Industrial-safety understanding requires more than detecting workers, equipment, and personal protective equipment. Models must also assess compliance, identify hazardous interactions, explain potential accident mechanisms, and recommend preventive actions. Existing safety datasets primarily focus on visual perception or isolated violation recognition and provide limited supervision for evidence-grounded reasoning. We introduce SafeSceneReason, a multimodal industrial-safety reasoning benchmark and companion training corpus that connects workplace scenes with knowledge from occupational accident investigations. SafeSceneReason combines two complementary data-construction pipelines. The scene-centric pipeline converts annotated workplace images into executable safety scene graphs and generates deterministic answers through program execution over objects, relations, and safety rules. The report-centric pipeline extracts figures and contextual evidence from accident reports and constructs multimodal questions using evidence graphs, explicit information boundaries, multi-step reasoning paths, and iterative verification. The resulting resource contains 110,581 verified scene-centric question--answer pairs and 13,114 refined report-centric question--answer pairs, covering perception, spatial and quantitative reasoning, compliance assessment, evidence synthesis, causal analysis, and mitigation-oriented decision making. Evaluation of representative proprietary and open-source vision--language models reveals substantial performance differences and persistent weaknesses in comparative, technical, and multi-evidence reasoning, demonstrating that strong general visual understanding does not yet guarantee reliable industrial-safety reasoning.

Uncovering the internal mechanisms underlying the safety capabilities of large language models (LLMs) is crucial for developing trustworthy artificial intelligence. Currently, mechanistic interpretability studies on multilingual safety are largely confined to local components, such as isolated neurons. However, this static and fragmented perspective overlooks the synergy among components and fails to elucidate how safety signals dynamically propagate within the model to drive safety decisions ultimately. In this work, we move beyond isolated neurons to identify and target the cross-layer functional pathways formed during safety signal propagation, thereby uncovering the mechanisms driving the cross-lingual safety gap. Specifically, we first identify monolingual safety pathways and validate their impact on refusing harmful requests. Subsequent cross-lingual analyses reveal a sparse subset of cross-lingual shared safety pathways, confirming that this intersection acts as the internal bridge transferring safety capabilities from high-resource (HR) languages to non-high-resource (NHR) languages. Building on these mechanistic findings, we propose a pathways-targeted alignment method based on the cross-lingual shared safety pathways. Experimental results show that updating only a small fraction of pathway parameters significantly improves safety in NHR languages while largely preserving the model's general capabilities.

Model merging has become the default way to give an aligned language model new skills without retraining: a practitioner folds task vectors from math, code, or domain specialists into a safety-aligned base using task arithmetic, TIES, or DARE. This convenience is known to carry a safety cost, but almost all of that evidence rests on static refusal tests: fixed harmful prompts scored for compliance. We argue this is misleading. Because safety alignment is "shallow," concentrated in the first few generated tokens, a merged model's static refusal can stay clean while a real adaptive attack still breaks it. We introduce SkillSafe-Bench, a controlled benchmark that scores skill-merged models on static refusal, adaptive jailbreak robustness, and capability retention under a conservative two-judge AND rule. Across six open-weight bases (five families, two scales), static safety does not predict robustness to attack: under a semantic template attack, safe-looking merges on the fragile bases (both Qwen scales and Gemma) are jailbroken 60-76% of the time while others (Llama, Phi-4) stay robust. We further show the static effect of merging is base-conditional, characterize same-recipe abliteration-style safety erosion through a data-free geometric signal (the overlap of a task vector with a safety subspace), and outline SubSafe-Merge, which projects this overlap away to remove that erosion at held capability. Adaptive evaluation is not optional for merged LLMs: the models that most need it look safe under static screening.

Current LLM safety guardrails face a fundamental tension: fine-tuning distorts pre-trained representations while generative judges incur prohibitive inference costs. We ask a complementary question: how far can safety be achieved through pure geometric reasoning over frozen representations, and where does it fail? We present HoloAegis, a minimally parametric topological inference framework that decouples representation from reasoning: an un-fine-tuned encoder maps text to the unit sphere S^{d-1}, and all decisions reduce to Gibbs-Boltzmann free-energy differences over pre-computed anchor centroids. We contribute a boundary-mapping study rather than a leaderboard claim. On a frozen three-benchmark protocol, HoloAegis (3.2 MB) statistically matches WildGuard-7B (14 GB) on toxicity (0.96 vs. 0.96), exceeds it on harmful behaviors (0.99 vs. 0.79), and cedes oversafety detection (0.62 vs. 0.98) -- while ShieldGemma-2B fails on indirect harms (0.34). These failure modes are complementary and mechanistically traceable: potential-difference scoring senses manifold clustering, whereas policy-conditioned LLM judging requires explicit taxonomy matching. We restate our Topological Boundary Stability conjecture in ratio form and validate it via reference-set bootstrap: anchor banks reduce score variance 4-15x and boundary displacement to approximately 0.44 + 0.23 sqrt(k/K) of the full-space estimator. Per-domain analysis further reveals that geometric separability tracks within-domain semantic homogeneity. Our results chart where geometric guardrails substitute for, and where they must defer to, LLM judges.

Deployed LLM safety guardrails are predominantly static: trained once and frozen at release, while new jailbreak techniques and previously un-addressed harmful categories emerge within days, leaving the defense perpetually a step behind. We present SESG (Self-Evolving Safety Guardrails), a multi-agent system running in production. SESG monitors the live traffic behind a deployed guardrail and surfaces two classes of failure: jailbreaks novel in form and harmful categories novel in content. Once a failure is confirmed, a generation agent synthesizes paired training data targeted at it; a validation agent rebalances the batch toward the direction in which the deployed model errs, so that the model's own mistakes steer its training set; and a routing agent matches the training action to the diagnosed gap and returns the next version to production. Over six rounds of live evolution (V0 to V6), a 1.7B guardrail adapts to a new threat in 16-24 hours, with about 2 hours of human effort, versus the 40-90 hours of the manual process it replaces. On six emerging threats, it outperforms static guardrails from 0.6B to 9B and an adaptive baseline while preserving its general screening competence. Since April 2026, SESG has been the primary update pipeline of Sangfor's guardrail, autonomously closing 14 of 15 new threat scenarios in two months. We release 9 test sets for the 6 new threats at https://github.com/Trams1017/SESG. Warning: This paper contains examples that may be harmful or offensive.

Steering vectors are a lightweight tool for controlling LLM behavior. However, emerging evidence shows that steering vectors can unintentionally compromise a model's safety mechanisms and increase compliance with harmful requests, while no effective mitigation yet exists. In this work, we show that this safety degradation arises from a separable component in the vector that disrupts the model's safety mechanisms but contributes little to the steering objective. We identify and remove this safety-degrading component, formulating the task as a constrained optimization problem solved through primal-dual updates, subject to preserving the intended steering effect and bounding false refusal. The resulting solution is both interpretable and surgical: the optimization recovers a single direction whose ablation from the steering vector restores model safety with minimal utility cost. Across models, steering behaviors, and attack suites, including unseen attacks types, our method substantially reduces steering-induced safety degradation while preserving the original steering effect with minimal impact on false refusal. Our method offers a post-hoc correction to steering vectors that mitigates their safety cost, and more broadly, it provides a general recipe for applying activation-level model interventions without paying a safety tax.

Youth increasingly turn to AI chatbots for social and emotional support, raising concerns about how these systems respond, especially in high-stakes situations. However, existing child safety evaluations of AI lack grounding in real-world harms that youth experience, rely on unvalidated assumptions about what counts as an appropriate output (e.g., refusal), and typically focus on detecting adversarial prompts or surface-level harms in outputs only. Thus, these evaluations can fail to detect responses that pose harm to youth in practice. To better understand the limitations of current evaluation practices, we conducted interviews with 19 practitioners working directly with youth in vulnerable situations, including social workers, therapists, and psychologists, asking them to reflect on chatbots' responses to risky situations commonly faced by youth, as established in prior empirical work. Practitioners identified chatbot behaviors likely to cause harm as well as those that could meaningfully support youth in difficult moments, discussed the role that chatbots should (and should not) play in these interactions, and offered concrete recommendations for improving chatbot responses. Based on these findings, we provide recommendations for AI child safety evaluation and infrastructure, and highlight the need for incorporating practitioners' perspectives into safety work.

Existing safety evaluation datasets for large language models (LLMs) predominantly focus on English and Western contexts, often overlooking the linguistic diversity and culturally grounded safety risks present in other languages. To address this gap, we introduce SurakshaEval, a novel safety benchmark composed of human-written prompts spanning real-world scenarios, explicitly designed for ten major Indian languages - Assamese, Bengali, Gujarati, Hindi, Kannada, Malayalam, Marathi, Punjabi, Tamil, and Telugu, along with English. SurakshaEval includes both generic prompts common across India and region- and language-specific prompts that capture localized sociocultural sensitivities. We benchmark a broad range of state-of-the-art LLMs on SurakshaEval, establish baseline safety performance, and identify recurring failure modes, including over-refusal, missed detection of implicit bias, and insufficient contextual awareness in regionally sensitive settings. Our results show that even strong multilingual LLMs struggle to reliably meet nuanced safety requirements when operating in Indic languages, particularly in native scripts. These findings highlight the urgent need for safety evaluation frameworks that incorporate region-specific data and structured assessment protocols, enabling the development and deployment of AI systems that operate securely, ethically, and in alignment with diverse societal values. Our code and data are available at https://github.com/debobanerjee/SurakshaEval. Warning: This paper contains text that may be offensive or unsafe.

Diffusion Large Language Models (DLLMs) replace autoregressive next-token prediction with iterative parallel denoising, yet their internal safety mechanisms remain poorly understood. In this work, we investigate DLLMs both as targets and as adversaries, exposing mechanistic vulnerabilities in diffusion-based alignment. We first show that safety alignment in DLLMs remains sparse and transferable across architectures. DLLMs initialized from autoregressive predecessors inherit the same mechanistic safety footprint as their source models, enabling transfer attacks via direct safety neuron mapping and pruning. Self-pruning increases attack success rates (ASR) from 2.6% to 73.8% on LLaDA and from 1.9% to 86.6% on Dream, while transfer pruning from Qwen2.5 increases ASR from 1.9% to 73.2% on Dream and from 7.0% to 86.3% on Fast-dLLM. Building on these findings, we introduce SN-Guided Diffusion, a fully offline black-box jailbreak framework that steers the diffusion process away from safety-triggering regions using a weighted safety neuron loss, which achieves near-perfect prompt separability (AUROC = 1.0 for benign-vs-jailbreak discrimination). Across multiple open and proprietary targets, our method achieves a transfer ASR of up to 77.1% on Llama-3-8B-Instruct, 86.9% on Qwen2.5-7B-Instruct, and 74.3% against Gemini-2.5-Flash-Lite, while requiring only 20 generation episodes per prompt. Compared to prior jailbreaking frameworks, our method achieves competitive transferability with orders-of-magnitude lower generation cost. Our codebase is available at https://github.com/ellyoana/sn-guided-diffusion.

Modern agent harnesses persist state across tasks and sessions through persistent carriers like memory, skills, tools, and shared artifacts. However, this capability creates delayed safety risks: attacker-influenced content can cross system boundaries and later affect the execution of a benign request. Existing benchmarks typically focus on a few carriers or harnesses, while end-to-end attack-success rates reveal little about how risks propagate. To this end, we present HarnessSafe, a benchmark comprising 328 executable cases across seven persistent-carrier families and evaluated on most mainstream agent harnesses. Each case is specified as a Persistent-Risk Lifecycle that traces attacker influence from its initial entry, through persistence across carriers and system boundaries, to a later benign trigger and an observable violation. We further introduce a multi-stage, trace-based evaluation that uses observable execution evidence to determine how far each attack chain progresses and where it is stopped. Experiments show that containment is carrier-specific and strongly depends on the harness-model configuration. Both the harness and model backend substantially shape containment outcomes, while attack success rates cannot reflect distinct lifecycle progression patterns.

Large language model (LLM) benchmark evaluations are routinely used to support claims about model safety, reliability, and deployment readiness. Yet most evaluations rely on a single access modality (model APIs), perform a single run per prompt, and report accuracy as the primary outcome metric, without accounting for conditions such as web search that may have effects on model behavior in deployment. We audit these assumptions for one of the most widely-used LLMs, comparing two modalities, ChatGPT's chat UI and OpenAI's API, with and without web search enabled. We use a stratified total sample of 401 prompts from two popular benchmarks, BBQ and SafetyBench, collecting 4,812 total responses across three repeated runs per prompt. Beyond standard performance measures, we evaluate model output dimensions including response consistency, response text similarity, citation grounding, and abstention behavior. For instance, chat UI responses were less accurate than API responses on both benchmarks with search disabled. Enabling web search reduced accuracy by up to 8 percentage points, and even reversed the direction of modality performance trends for one benchmark. Repeated runs of the same prompt produced inconsistent responses in up to 21% of prompts. The two modalities also grounded answers in different citations, and abstention behavior was also inconsistent across both modalities. These results illustrate that, even within a model family, reporting only simple accuracy metrics can obscure important forms of model behavioral variation relevant to AI safety assessments. We argue that AI safety evaluations should systematically account for modality, multi-run consistency, search conditions, and response-level behaviors to better reflect how deployed AI systems behave in practice.

Timely anticipation of physical hazards is essential for real-world safety, yet existing MLLM evaluations focus on harmful content or general risks, leaving proactive physical hazard prediction underexplored. Sports provide a well-suited testbed: accident causes span diverse injury dimensions and pre-accident spatiotemporal cues draw on reasoning capabilities shared with broader safety domains such as autonomous driving and fall detection. We introduce SPRINT (Sports Proactive Risk INference Testbed), a benchmark of 2,888 real-world sports videos (2,440 accident, 448 safe controls) spanning 14 sports and 3 environmental settings. Accident videos feature fine-grained annotations of early hazard cues, accident timing, and hierarchical causes; safe videos are manually verified as accident-free and serve to diagnose prompt-induced false alarms. Evaluating state-of-the-art MLLMs under diverse prompts and temporal windows reveals a sharp gap between hazard sensitivity and understanding: the best model exceeds 95% in signaling hazards yet falls below 50% in identifying their causes. Diagnostic experiments further show that explicit danger queries trigger severe false alarms even on hazard-free videos. These findings indicate that current MLLMs exhibit only superficial proactive safety, lacking stable, cause-grounded early warning, and underscore the need for reliable proactive safety in dynamic physical environments. Data and code will be open-sourced upon acceptance.

Large language models typically undergo post-training to align them with safety policies but there exist many sophisticated jailbreaks that sidestep established safeguards. For instance, prior work by Andriushchenko et al. (2025) has found that changing the grammatical tense from present to past can be enough to elicit harmful responses. In this work, we uncover a more general failure of non-imperative syntactic forms. We demonstrate that this syntactic vulnerability exists in 16 models up to 70B parameters, using behavioral evaluation. To investigate the root cause, we apply causal mediation analysis, finding that refusal is partially conditioned on upstream syntactic features. By steering these purely syntactic features we are able to trigger and suppress refusal. Finally, we trace this ill-conditioning to linguistically biased post-training data of open-source models and show that increasing syntactic diversity can mitigate the issue. Our findings suggest that current alignment approaches introduce confounders that prevent a pure semantic grounding of the refusal decision.

Service robots operate in household environments shared with humans, pets, and everyday objects, where they are highly susceptible to failures such as software crashes, hardware degradation, or unpredictable interactions. While roboticists strive to minimize failures, some remain inevitable, making it critical to mitigate their potential consequences for safe and reliable deployment. This paper introduces a novel safety formulation that evaluates both the probability of impactful interactions between robots and surrounding entities during failures, and the severity of their outcomes. By quantifying the impact of failures on different entities, our approach enables robots to make informed planning decisions that balance safety with task efficiency. To support systematic evaluation, we also present FailBench, a MuJoCo-based simulation framework for studying robot-environment interactions under diverse failure modes, including sensing issues and actuator malfunctions. Together, our safety formulation and FailBench provide a foundation for developing safer and more robust motion plans and learned policies in real-world household environments.

Defensive driving scores are useful only when they preserve distinctions between policies that observe surrounding actors and those that do not. Re-simulation benchmarks may use reference-conditioned forgiveness, under which an agent receives credit when the logged human reference fails a compliance channel. When agent and reference share an unstable rollout transformation, this rule can propagate shared reference failures into broad compliance credit. We audit this risk in NAVSIM v2.2 original scene single-stage scoring. Under the affected documented-stack condition on the audited numerical backend, the route-blind Ignore-All probe and a route-aware actor-blind probe outrank human replay and PDM-Closed over the complete 12,146-token navtest split. A fresh installation following the public specification reproduces rollout divergence on a fixed 32-token diagnostic set. A same-source dependency stack control and an exact-input diagnostic isolate dependency-sensitive numerical behavior in the shared velocity refit. On a 450-token control pool, replacing only the solver eliminates rollout divergence and restores blind-last ordering while keeping forgiveness enabled. Thus, the numerical instability is the direct trigger. Reference-conditioned forgiveness propagates the resulting shared reference failures into compliance credit. We contribute an audit protocol requiring score basis and stack disclosure, blind probes, overwrite reporting, and rollout stability tests before using such scores for defensive driving claims.

Task-specific fine-tuning can improve the performance of large language models (LLMs) on downstream tasks. However, our study reveals that task-specific fine-tuning can also weaken the safety guardrails of aligned LLMs. A widely adopted strategy for preserving safety during fine-tuning is to incorporate safety data. Although previous studies have shown that randomly mixing safety data can alleviate safety degradation, the underlying principle determining why some safety examples are more effective than others still remains unclear. In this paper, we propose DataRx, a missingness-aware sampling method for selecting safety-critical examples. DataRx is based on the hypothesis that a safety sample is more effective when the selected examples provide safety signals that fill the missing parts of LLMs' safety capabilities. DataRx's key insight is leveraging high-dimensional hidden representations rather than discrete tokens to quantify the safety signal gap between the target model's native response and the safety reference response. The results show that, with only 1% additional safety samples from BeaverTails, DataRx reduces the average attack success rate of Llama3-8B-Instruct across seven downstream tasks from 59.23% under random sampling to 13.70%. In addition, DataRx can be combined with the existing safety data synthesis method to further enhance safety defenses during fine-tuning. We hope that DataRx will inspire more data-centric defense research.

Long-horizon agents increasingly use persistent memory and tools to take actions with external side effects. A central failure mode is premature commitment: an agent acts before resolving whether its memory grounding is stale, conflicting, incomplete, or corrupted. We formalize this problem as safe commitment under memory uncertainty and introduce SafeCommit, a risk controlled layer between agent reasoning and external execution. The layer constructs a calibrated set of plausible latent worlds from memory, observations, tool outputs, provenance, and policy constraints. It permits a side effectful action only when a conformal action certificate shows that the action is safe in every retained world. Otherwise, it selects a low-side-effect probe that targets the worlds blocking certification, or returns a conservative fallback. Under calibrated world coverage, the probability of an unsafe certified commit is at most the target level α; with imperfect world proposal, the bound separates calibration and representation error. A dependency-free controlled simulator illustrates the safety-utility tradeoff and reproduces all reported results with one command. The goal is to offer a concrete approach for deciding not only what an agent should do, but when the available evidence is sufficient to safely do it.

Vision-language-action policies often fail under deployment-time distribution shifts such as clutter, distractor objects, lighting changes, novel objects, altered initial states, and reworded instructions. Hidden-state-based risk probes combined with functional conformal prediction can detect rollout failures, but their reliability depends on calibration data matching deployment conditions. We introduce SAFECAST, which leverages contrast set perturbations to improve hidden-state probe training and calibration for deployment time shift. SAFECAST statistically significantly improves failure detection ROC-AUC scores over a state of the art baseline in both real-world DROID and LIBERO simulation experiments across multiple VLM backbones. We further find that SAFECAST benefits most when both visual and language contrast set perturbations are used to augment data, and that with contrast set perturbations, sim-to-real calibration leads to better probes than using real rollout data only.

This white paper presents ADMITBench, a reference framework for evaluating industrial LLM advisories at the level of the proposed action. The framework implements a versioned, safety-governed evaluation contract that checks whether a recommendation is supported by the available evidence, permitted under the stated authority and procedure, and acceptable under the plant-specific consequence checks encoded in the selected evaluation profile. In this report, \emph{safety-governed} means that eligibility is determined through explicit, non-compensatory checks derived from a versioned plant profile; it does not mean that the evaluator, model, or plant has been safety-certified. Release 0.1.0 is a public reference implementation for technical and research evaluation, not an authorisation for physical execution.

Safety shields are runtime enforcement mechanisms that restrict the actions of a controller to guarantee safety. Classical shields are usually synthesised for state predicates: the current physical state is either safe or unsafe, and the shield disables precisely those actions that can force the system into an unsafe state in the future. In many cyber-physical applications this view is too coarse. A vehicle approaching an obstacle should not only avoid collision, but also respect speed regulations, force limits induced by acceleration, and jerk limits to prevent injuries. From a physical perspective, these requirements are predicated over the derivatives of the state. This paper develops a finite-state safety-game construction for such high-order smoothness constraints. We define differential safety properties using finite differences over a discretised state space, characterise their expressiveness, and reduce shield synthesis to an ordinary safety game over a history state space. We give a synthesis algorithm whose shields store exactly $k$ past states for properties of order $k$ and prove that this memory is necessary. We describe an iterative synthesis procedure for a maximally permissive shield that operates over hierarchies of derivative constraints. The algorithm solves constraints iteratively in increasing order and uses the solution at each iteration to prune the state space for the next constraint. This makes shield synthesis more efficient in practice, as the algorithm refrains from exploring large regions of the state space that are known to be unsafe.

Applying a valid medication-safety rule when its patient-specific conditions are not met can produce an incorrect decision. Existing medical evaluations largely use isolated and fixed scenarios. A model may therefore answer correctly by recalling a drug-risk association without showing that it used patient information to decide whether the rule applies. To address this gap, we introduce MedPIC-Bench, a benchmark of source-verifiable recommendations and expert-validated questions for patient-specific medication-safety reasoning. It combines guideline-following questions with paired counterfactual questions in which a controlled change in patient information changes whether a rule applies. The benchmark contains 467 questions annotated along six clinical and reasoning dimensions. Across 28 medical-specific, general, and proprietary LLMs, every model performs worse on counterfactual questions, with mean accuracy falling from 63.6% to 45.1%. Models perform well when an explicit patient attribute directly signals a familiar contraindication, but struggle when patient information must narrow or withdraw a safety warning. Model rationales often acknowledge the changed patient information, yet the final answers retain the previous safety judgment. This vulnerability persists among medical-specific LLMs, whose average CF performance trails that of general LLMs. MedPIC-Bench therefore makes conditional rule application measurable and highlights the limitations of static medication-safety accuracy for assessing patient-specific reliability.

Industrial humanoid robots are constrained less by locomotion or manipulation capability than by the immaturity of functional safety certification for legged platforms. The root difficulty is that the safe state of a legged robot is an actively-controlled state, which violates the fail-passive assumption underlying ISO13849-1 / EN60204-1: removing power from a walking biped causes an uncontrolled fall, so classical de-energization is itself a hazard. We term this the fail-passive gap and use a certified external safety chain (light curtain, emergency stop, fail-safe input, fail-safe PLC, and wireless PROFIsafe) as an instrument to locate it precisely: because the external chain is closed and quantifiable with established methods (PFHD, DC, CCF, PL/SILCL), the residual uncertifiable element is pinpointed to the robot-side reaction chain. Using a Siemens fail-safe S7-1500 emergency-stop reference, we show its certifiable Reaction subsystem is contactor-based power removal (Stop Category0)---exactly the element a balancing humanoid cannot have. We deliberately do not claim end-to-end certified PLe / SIL3. We validate the approach on a Unitree G1 EDU pick-and-place cell in a 3m x 1.5m semi-enclosed workspace, and contribute a humanoid-specific analysis of the active safe state (fall-as-hazard, single-support stop bounds, balancing-policy residual risk, ISO13855 separation) and a provenance-labeled timing budget. Hosting an industrial software-defined automation (SDA) controller on the robot, co-located with the balancing policy, moves robot-side PROFINET/PROFIsafe reception onto a standardized IEC~61131-3 interface; because the G1's onboard compute is not safety-rated hardware, this endpoint is not a certified safety runtime, which reinforces rather than resolves the fail-passive gap and localizes it to the SDA-to-balancing-policy interface.

Vision-language models (VLMs), including medical specialists, are increasingly proposed for medical imaging, yet their stated confidence is rarely evaluated separately from correctness. We use brain MRI as a controlled, high-stakes testbed for a broader failure mode in frontier multimodal systems: models can appear competent while lacking reliable self-knowledge. We present an automatically graded behavioral audit and pilot study of six instruction-tuned VLMs (five general-purpose and one medical specialist) on 4,102 images (4,032 axial/coronal/sagittal MRI slices from 250 subjects plus 70 non-brain/noise controls), with labels derived from public metadata and released expert segmentation masks rather than new human annotation. Across models, answer coverage is near-complete, but verbalized-confidence calibration is poor: ECE ranges from 0.27 to 0.40, mean confidence on incorrect answers ranges from 0.82 to 0.97, and 33-46% of answered items are high-confidence errors. The most accurate model is also the most confident on its errors, while a base/specialist family contrast suggests that medical adaptation improves tumor-presence detection without improving confidence reliability. Open-ended diagnostics further show that hallucination and abstention vary separately from multiple-choice accuracy. These findings argue that medical-image VLM evaluation should report verbalized-confidence reliability, confident error, hallucination, and abstention alongside accuracy.

Large Language Model (LLM) agents rely on multi-stage agentic workflows, with stages such as memory, planning, and tool execution, to accomplish complex tasks. However, risks may emerge at different stages, propagate across steps, and become difficult to detect and mitigate. Existing safety methods protect only isolated stages and are difficult to integrate, leaving agents without comprehensive protection throughout the workflow. To address these limitations, we introduce Stage-Specific Safety Skills, a unified abstraction that represents heterogeneous safety designs as reusable and composable components with explicit stage semantics. We further develop an automated transformation pipeline that converts existing safety designs into reusable safety skills and establish a community-driven safety skill library. Building on this abstraction, we propose $S^3$, a multi-stage defense framework in which a guard agent orchestrates stage-specific safety skills for risk detection and mitigation throughout the agentic workflow. We also construct the Multi-Stage Risk Benchmark (MSRB) to evaluate representative risks across workflow stages. Experimental results show that $S^3$ consistently outperforms representative state-of-the-art baselines in both safety effectiveness and utility preservation. These results demonstrate the potential of stage-specific safety skills as a scalable and composable foundation for building resilient and trustworthy agent systems.

With the rapid release of open-weight large foundation models, safety threats are shifting from black-box jailbreaks to neuron-level white-box attacks that directly identify and manipulate safety-related neurons. Existing alignment methods often investigate the safety behavior on a small number of neurons, creating fragile single point of failure with limited redundancy. To address this issue, we propose distributed safety alignment (DSA), which redundantly encodes safety capabilities across multiple computational neurons, ensuring that the model maintains its safety baseline even when critical safety neurons are disrupted. Specifically, we localize the intervention to the inputs of the down-projection layers in language-side feed-forward networks and treat each feature coordinate as the activation of an individual neuron. DSA then combines neuron activations with loss gradients to compute a direction-aware first-order Taylor score that globally identifies the neurons that contribute most to the current refusal behavior of the model. Finally, targeted disruption via deterministic masking and stochastic dropout is coupled, forcing the model to abandon narrow safety neurons and redundantly encode safety behavior across multiple compensatory neurons. Extensive experiments show that DSA substantially improves robustness against white-box neuron-level safety attacks while preserving the model's general language and multimodal utility.

With the widespread deployment of large foundation models (LFMs) in open environments, safety threats are shifting from black-box jailbreaks toward white-box attacks that directly identify and disrupt internal safety neurons or routes. However, existing safety defenses often rely on static safety units or fixed refusal pathways, leaving models highly vulnerable to targeted route-level white-box attacks. For that, we propose dynamic routing adaptive alignment (DRAA), a framework that introduces dynamic compensatory routes to preserve robust refusal behavior when the safety route is compromised. Specifically, we first identify and localize the model's safety route by contrasting internal activations between safe and unsafe calibration samples. DRAA then masks this safety route to induce causal failure cases and selectively mines the resulting defense failures, thereby constructing failure-aware preference pairs. Extensive experiments demonstrate that DRAA effectively restructures the underlying pathway dependence of model safety, substantially improving robustness against route-level white-box attacks, while preserving general utility.

Design campaigns in chemistry, materials science, and machine learning share a bottleneck: determining how good a candidate truly is requires an expensive evaluation - an experiment, a first-principles simulation, or a full training run. Machine-learning surrogates that predict these outcomes are increasingly used not only to propose candidates but to grade them, and even to feed their own predictions back into the search as though they were measurements. Through mathematical analysis validated on three exhaustively ground-truthed design tasks, we establish when this practice is safe, what any certificate of safety must cost, and when the substitution provably pays. Predictive accuracy cannot anchor trust: near-perfect R^2 is compatible with worst-possible selections, and screening N candidates inflates the over-prediction at the selected candidate by a quantifiable "selection tax" with matching upper and lower bounds. Safety follows instead from an architectural rule - predictions may propose and train without restriction, but every certified conclusion must rest on true evaluations - which is sufficient with no assumptions on the surrogate, and necessary, since admitting predictions into certification with the standing of measurements opens a deterministic self-confirmation failure mode. We derive the minimal criterion under which a model may act as an oracle (rank preservation, not accuracy), show that trust must be purchased through selection-aware audits that are optimal in query complexity, and prove a dichotomy fixing when audited surrogates cut certified evaluation cost. Across 432 surrogate fits over six task-regime conditions, the audit statistic tracks deployed search performance at Spearman rank correlation 0.80-0.99, while the rank correlation of R^2 with deployed regret falls as low as 0.33; audited screening reduces certified oracle cost by a measured factor of 25.

We present ArabicDialectSafety, a human-curated Arabic safety dataset of 25,071 prompts covering six Arabic varieties: Modern Standard Arabic, Syrian, Egyptian, Algerian, Palestinian, and Moroccan. The dataset is annotated with dialect labels and seven fine-grained harm categories. We introduce a dual-task evaluation framework for binary safe/unsafe detection and granular harm classification across dialects. Benchmarking seven supervised and generative models, we find that fine-tuned MARBERTv2 achieves the strongest performance, with Macro-F1 scores of 0.95 for binary classification and 0.90 for granular classification, substantially outperforming prompted frontier LLMs, including Arabic-specialized models. Our analyses show that dialect conditioning is most effective when integrated at the representation level, while significant performance gaps remain for low-resource Maghrebi dialects. We further evaluate seven frontier LLMs as response generators on harmful dialectal Arabic prompts and observe unsafe generation rates below 5 percent across models. We release the dataset and code upon acceptance to support future research on dialect-aware Arabic safety evaluation. Warning: This paper contains examples of harmful and potentially offensive content included solely for research purposes.

A benchmark score is a measurement instrument, yet most benchmarks read each item at a single canonical surface form. We ask whether that reading is faithful: when an item's intent is held fixed and only its meaning-preserving surface form varies, does the canonical-form score estimate model behavior well, and how much of any variation is decoding/judge noise rather than signal? We instantiate this in safety, a high-stakes setting with no gold label to average toward. To avoid prior confounds, we pre-author the reformulations (refusal-free, mostly non-LLM: machine back-translation and a Matrix-Language-Frame code-switch generator) so an identical surface form reaches every model, score all responses with one human-anchored, vendor-neutral judge (Claude, kappa = 0.86 vs. human on unsafe compliance, stable across languages, cross-checked by GPT-4o), and verify intent preservation. On 370 seeds x 5 surface forms x 5 models, no single transformation is uniformly most dangerous (6 of 20 per-transformation McNemar tests survive correction, most protective). Yet evaluating only the canonical prompt underestimates unsafe compliance: the union of unsafe outcomes across forms exceeds even the worst single form by 3.3-12.9 pp, with bootstrap 95% CIs excluding zero for all five models, and 5-13% of seeds safe on canonical are unsafe under some reformulation -- above a zero stochasticity floor (canonical resampled five times at temperature 0 gives 0/370 new exposures). The size of this gap is model-dependent (largest on Gemini 2.5 Pro). One form recovers only ~53% of a model's observed unsafe surface and about three reach 85% -- a redundancy characterization of this form set, not of a defined population. A benign control (XSTest) suggests the instability is bidirectional, though the benign and harmful pools are not item-matched. We release the dataset, code, and per-response labels.

AI agents operate in persistent environments where early state changes can influence decisions far into the future. Unlike conventional language-model interactions, agent behavior is mediated through a shared state that is repeatedly modified and reused across long-horizon workflows. Current safety benchmarks often fail to capture these cumulative risks because they focus on short, static tasks. To address these limitations, we introduce OpenART, an open-ended arena for scalable agent red teaming through environment evolution. OpenART provides over 10,000 validated stateful scenarios across 50 domains, drawing from a pool of more than 500,000 tools and skills. These tasks require a median of 97 tool calls and enable unified evaluation across 75 different agent-model configurations. To systematically explore these evolving attack surfaces, we propose the Evolutionary Markov Hypergraph Attack (EMHA). EMHA is a black-box policy that performs feedback-driven environment evolution by coordinating authorized state transitions without requiring parameter updates. Throughout the evaluation, task objectives remain fixed while only the environment state changes. Across all configurations, EMHA achieves a pooled Attack Success Rate (ASR) of 85.0%. Its advantage over instruction-only evolution increases from approximately 2% on simple environments to over 17% on the most complex ones, demonstrating that environment evolution increasingly exposes safety failures as task complexity grows. Furthermore, our analysis shows that the specific runtime implementation of an agent explains a significant portion of safety variation beyond the underlying model's capabilities. These results establish OpenART as a scalable foundation for studying agent safety in complex, evolving environments.

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

Deploying drone swarms to track a dynamic target in cluttered environments presents severe computational and safety challenges. We propose MROPE, a hierarchical strategy that decouples the cooperative monitoring mission from strict local safety requirements. To overcome the computational bottlenecks typical of dense spaces, our approach dynamically aggregates complex obstacle geometries into a single safe bounding ellipse for each drone. Methodologically, this architecture is realized by combining distributed aggregative optimization for high-level swarm coordination, a decentralized consensus scheme for the safe area computation, and local Predictive Safety Filters (PSF) for real-time collision avoidance. Virtual and real-world experiments validate the framework, demonstrating superior real-time efficiency and scalability compared to centralized approaches.

Although Large Language Models (LLMs) have demonstrated promising safety performance, extending them to Multimodal Large Language Models (MLLMs) exposes a significant gap between expanded multimodal capabilities and existing safety mechanisms. Current defenses remain predominantly confined to specific modal settings, thereby limiting their robustness against broader cross-modal threats. To bridge this gap, we introduce SafeNexus, a cross-modal safety alignment framework that adopts a dedicated neuron-level intervention strategy. First, we formulate a neuron localization paradigm that identifies functionally specialized neurons by characterizing intermediate-layer activation patterns and quantifying their functional salience through importance scoring. Building upon this paradigm, we exploit contrastive data to identify modality-bound safety neurons (BS-Neurons), and validate their role in regulating safety behavior within each modality via targeted suppression. Further cross-modal analysis defines modality-universal safety neurons (US-Neurons) as the shared subset of BS-Neurons identified across individual modalities, serving as the core for defending against harmful cross-modal attacks. We observe that suppressing these neurons substantially degrades safety performance across modalities, while leaving overall utility largely unaffected. Building on these insights, we propose two safety alignment strategies: activation-level safety amplifier and safety neuron calibrator. The proposed strategies enhance model safety through two distinct routes: the former amplifies the activation magnitudes of US-Neurons, while the latter selectively calibrates them via targeted fine-tuning. Extensive experiments demonstrate that our method outperforms prevailing state-of-the-art approaches on safety benchmarks spanning diverse modality combinations, while effectively preserving utility.

We present PAC-MAN, a perception-aware CBF-RL framework that couples control-barrier safety with deployment-realistic onboard sensing for whole-body humanoid dodgeball. The deployed policy sees the ball only as segmentation-masked depth from a head-mounted camera, while training-time CBF guidance represents clearance to every body link, and an adversarial motion prior regularizes the resulting evasive reflexes. We evaluate on a controlled any-link contact benchmark with seeded throws in two regimes: single throws and a deployment loop in which the robot walks back to its station and recovers between throws. On this benchmark, the policy comes within a few points of a privileged state oracle: a fixed onboard camera alone is adequate for evasion. We find that usable barrier structure depends on perceptual observability: Joint-CBF gives the best performance with accurate ball states, degrades under fixed-camera observations when used only as training guidance, and recovers with a ball-tracking gimbal or privileged runtime filter. We therefore deploy a lightweight Link-CBF policy zero-shot on the Unitree G1 in the real world, where it tolerates imperfect perception, succeeds on 95% of throws, and uses semantic segmentation to dodge different balls.

In this paper we present an active, constantly updated AI benchmark which measures the integrity of frontier language models against being co-opted for use by authoritarian state "information operations": intentional, coordinated activities by one state to influence public opinion and information ecosystems in another state. These information operations are a well documented, persistent threat against contemporary democracy. Our benchmark is based on real examples from over 2,100 information operations drawn from a live monitoring pipeline which tracks online information assets with links to authoritarian regimes. Alongside this paper, we also release a companion website that updates the benchmark weekly with new claims. The dynamic nature of this public facing benchmark makes it resistant to saturation. In the benchmark, we test 17 models from 8 providers across four prompt framings. We find that most models can be co-opted for information operations at least some of the time. Integrity scores, defined as the share of judged responses in which the model neither preserved nor amplified the claim, range from 9.3% to 91%, an 81.7-percentage-point spread not explained by model size. Models approach participation in information operations in a variety of ways. Some models fabricate details and produce output more harmful than the original input claim; others make claims less harmful even while complying and producing some output. Fact-checking rates vary from 3.2% to 80.8%. Integrity against information operations is at least partly related to refusal to produce content even for benign claims, illustrating the challenge of balancing model usability with safety. Overall, our results show the potential for contemporary information operations to be substantially aided by frontier AI models.

Large language model safeguards decide whether to answer before seeing how an answer will be used. This creates a basic problem for dual-use tasks: the same answer can help an authorized professional or an attacker, while an attacker can imitate a benign request and interaction history. We separate the capability released by the model from the evidence available about downstream use. When that evidence is copyable, we derive the exact worst-case floor on attacker assistance while preserving useful answers. The result yields a safety trilemma: Useful Capability, Reliable Safety, and Open Access cannot coexist. We then show how a trusted credential can complement existing safeguards by adding hard-to-copy information that predicts actual downstream use, and identify the stronger condition needed to eliminate the floor. Evidence from dual-use evaluations, adaptive attacks, and deployed trusted-access programs supports the practical relevance of these conditions.

As large vision-language models (LVLMs) are deployed globally, the combination of multilingual instructions and visual information makes malicious attacks more covert and sophisticated than ever before. However, existing methods isolate language and modality defenses, which, coupled with the scarcity of safety data and high fine-tuning costs, makes it difficult for models to defend against compound attacks. To address this severe challenge, we propose a neuron-level cross-dimensional safety alignment framework driven by modality- and language-shared safety neurons (MLS-Neurons). First, we identify monolingual and unimodal safety neurons by comparing responses to harmful and benign samples, quantifying functional saliency through activation strength and downstream impact. Then, by intersecting these unimodal neurons within each language, we extract modality-shared safety neurons (MS-Neurons) responsive to both visual and textual risks, bridging the safety representation gap between modalities. Furthermore, using English as a semantic anchor, we intersect MS-Neurons across languages to identify modality- and language-shared safety neurons (MLS-Neurons), serving as key defenses against compound attacks. Finally, we update only this minimal subset of shared neurons (~0.03% of parameters), transferring English-only safety supervision to multilingual and multimodal scenarios. Extensive experiments show that our method significantly outperforms state-of-the-art approaches across diverse multilingual and multimodal safety benchmarks while preserving general utility.

Accurate cell segmentation and classification are foundational to digital pathology, enabling quantitative tissue analysis for diagnosis and treatment planning. Encoder-decoder architectures that fuse multi-scale features through skip connections have become the dominant paradigm for this task, yet standard direct skip connections treat every spatial location equally, which leads to redundant and potentially conflicting information reaching the decoder. To overcome this problem, various gating mechanisms have been introduced, but most of them operate solely on filtering encoder information, neglecting the benefit of global contextual information from the decoder. This study proposes replacing conventional skip connections in a CellViT-based model with a novel Spatial Attention Fusion (SAF) Gating module. Each SAF gate concatenates the encoder skip and upsampled decoder features, compresses them through two pointwise convolutions with an intermediate ReLU, and applies a channel-wise softmax to produce a per-pixel "heatmap of trust" that sums to unity at every spatial location, allowing the network to learn where each source is most trustworthy. The resulting fused features improve the model's ability to detect the minority "Dead" class, which in turn enhances the multi-class panoptic quality (mPQ) on the PanNuke dataset. SAF Gating is compared against six gating alternatives including no gating, attention gates, squeeze-and-excitation, CBAM, cross-attention, and attentional feature fusion on PanNuke and MoNuSeg datasets. SAF Gating achieves the highest mPQ (0.471), a gain driven primarily by a 14.5-point improvement in Dead-class F1 score compared to ungated CellViT baseline.

Agent-safety benchmarks measure different behaviors, and their scores get quoted interchangeably as an agent's safety. We treat four of them (R-Judge, InjecAgent, AgentHarm, AgentDojo) as measurements to be validated, running each under its official implementation and author-provided scorer on up to 22 models, with MMLU and GPQA measured by us under one protocol as a capability composite. The metric is the first problem. On any binary trace-judgment benchmark scored by $F_1$, an ``always positive'' policy attains $F_1 = 2π/(1+π)$; on R-Judge that is $0.690$, above five of the 21 models that actually discriminate. The three broad-coverage benchmarks then rank the same 18 models differently, and the trade-off behind that disagreement is a small-panel artifact: R-Judge specificity against AgentHarm safety correlates $-0.64$ at $n{=}7$ and $+0.02$ at $n{=}18$, and a quarter of random size-7 subsets reach $|ρ| \geq 0.5$ around that near-zero value. Held-out validity turns on which outcome you pick. Capability predicts task success ($ρ{=}{+}0.60$) but correlates negatively with misalignment safety ($ρ{=}{-}0.44$, $n{=}21$). On their paired $n{=}20$ panel, the corresponding contrast is $Δ{=}{-}1.00$ (95% CI $[-1.48, -0.49]$, $p<0.001$), and it survives leave-one-organization-out and organization-clustered bootstrap analyses. On an expanded 41-model panel, the misalignment correlation weakens to $-0.16$ (95% CI $[-0.54, +0.22]$) and jailbreak strengthens to $+0.34$, though neither change is significant. \mbox{AgentHarm} shows the strongest held-out association, $ρ{=}{+}0.72$ with three-template jailbreak safety after controlling capability. But both instruments score harmful compliance, so this is evidence of convergent validity rather than general safety. Naming the benchmark, metric, target behavior, and model panel is the minimum a safety claim needs.

Safety-critical IoT systems such as industrial closed-loop control, V2X coordination, and remote teleoperation require every sensor's peak Age of Information (peak AoI, also abbreviated PAoI) to stay below a hard per-slot deadline, not merely an average bound. Existing approaches meet this requirement only under restrictive assumptions: stochastic channels for Whittle-index AoI, simulator rollouts for deep reinforcement learning, or sublinear cumulative violation for long-term constrained online convex optimization. Under adversarial coefficients, OCO-PAoI-Hard guarantees zero per-slot violation of the modeled AoI state under one-step viability and O(sqrt(T)) regret against any static safe comparator; packet-level safety requires stronger service assumptions. Our key observation is that the fractional peak-AoI deadline collapses exactly to an affine half-space constraint on the resource-allocation vector, turning hard real-time scheduling into time-varying constrained online convex optimization over a polyhedral safe set. A strictly causal proposal-shield-update loop enforces feasibility through one Euclidean projection per slot, the gradient step preserves no-regret behavior, and the classical virtual queue is reduced to an a-posteriori certificate. We establish closed-form static and dynamic regret bounds, a matching Omega(sqrt(T)) minimax lower bound, a margin-safe variant against execution noise, and a deadline-induced competitive ratio. On a four-sensor adversarial fluid-model trap channel, OCO-PAoI-Hard attains zero modeled-state deadline violations across all ten seeds, while four representative baselines miss between 1.65 percent and 64.0 percent of slots, and the empirical normalized regret stays below the theoretical envelope across two orders of magnitude in T.

Post-training alignment in large reasoning models (LRMs) has significantly improved their adaptability to diverse safety compliance settings. However, as LRMs personalization for downstream users takes center stage, the demand for varying levels of policy compliance grows as different user-specific LRMs must adhere to distinct subsets of safety policies. Training a separate LRM for each policy subset introduces severe combinatorial overhead. While in context learning methods overcome this combinatorial overhead, they introduce additional computational challenges associated with long context generation. To address this challenge, we propose \ours, a unified adaptive hypernetwork-based framework for multi-policy compliance. In our framework, safety policies serve as customizable inputs to a LoRA adapter generator, which learns to produce policy compliant LoRA weights for downstream LRM. When added to the LRM these weights enable the generation of responses compliant with the specified policy subsets. In this work, we demonstrate that training such a hypernetwork enables on-demand policy adjustments on a single LRM without sacrificing task performance across reasoning models of different sized and different evaluation datasets. This highlights the effectiveness and practicality of adaptive hypernetwork based alignment in LRMs.

Fine-tuning is the dominant paradigm for specializing large language models (LLMs), yet it exposes a critical vulnerability: malicious data providers can embed harmful behaviors into downstream corpora, creating models that retain professional skills while violating human values on demand. Existing safety-realignment defenses often fail in practice due to three key limitations: they frequently cause catastrophic forgetting of specialized skills; their effectiveness collapses when the defender cannot observe the attacker's prompt template; and successfully realigned models remain susceptible to re-jailbreaking via simple system prompt switches. To address these challenges, we propose Routing-based On-Policy Distillation (ROPD), a novel realignment framework that models the divergence between aligned and compromised output probability distributions rather than fitting specific prompt templates. We conduct extensive experiments comparing ROPD against four state-of-the-art baselines across three datasets and three base models with varying alignment strengths. Our results demonstrate that when baseline defenses face template mismatches, often accompanied by severe degradation in downstream task performance. In contrast, ROPD substantially mitigates template-mismatch risks, maintaining superior robustness in both defense effectiveness and capability preservation. While our analysis indicates ROPD is not entirely immune to template shifts, its performance degradation is negligible compared to existing methods, establishing a new standard for robust LLM realignment.

As large language models (LLMs) evolve from standalone assistants into autonomous agents, ensuring their safety requires shifting beyond pointwise risk assessment to understand how risks emerge and unfold over long-horizon trajectories. In multi-turn interactions, malicious intent can be decomposed across seemingly harmless turns and gradually reconstructed through interaction trajectories, eventually resulting in safety failures. Existing safeguards remain largely reactive, detecting manifested violations while lacking the ability to predict latent risk evolution and enable preemptive prevention. To address this limitation, we propose Recast, a safety risk forecasting framework that advances LLM safeguarding beyond turn-level violation detection to trajectory-level risk prediction. Recast first retrieves risk-relevant evidence from both short-term dialogue progression and long-term historical context via a dual-scale trajectory view. It then models compositional risk evolution by capturing the current risk configuration and its temporal dynamics. Finally, a causal temporal encoder learns latent risk evolution patterns and predicts the distribution of future risk emergence turns. Extensive experiments across 7 risk categories show that Recast predicts 88.3% of future safety failures with an average lead time of 2.41 turns, while maintaining a false alarm rate of 12.3%, showcasing the effectiveness of trajectory-level forecasting in identifying emerging risks before safety violations occur.

This paper presents a radial basis function network (RBFN)-informed motion planning framework for safe and efficient urban autonomous driving. The proposed approach combines RBFN-based candidate trajectory generation with an analytic collision probability assessment and optimization-based trajectory refinement. The network learns jerk-minimal trajectories, enabling the MPC to operate within a reduced and dynamically consistent search space. Candidate motion primitives are selected based on an accurate probabilistic risk measure. This design decreases solver complexity while preserving safety and constraint satisfaction. The framework is evaluated in numerous urban driving scenarios. Results demonstrate improved risk awareness and fewer vehicle-limit violations compared to benchmark methods. The proposed approach integrates learning-based trajectories into optimization-based motion planning, thereby ensuring safety and interpretability.

Reliable visual safety understanding in real-world scenarios demands more than just object recognition; it requires causal reasoning under epistemic uncertainty. While Large Vision-Language Models (LVLMs) demonstrate impressive semantic alignment on standard benchmarks, they often struggle to distinguish between superficial correlation and genuine forensic logic when grounded in the dynamic, partially observable nature of first-person experiences. Existing evaluations, dominated by third-person surveillance footage and binary classification metrics, fail to expose this cognitive gap. To address this, we introduce EgoSafe-Bench, a benchmark specifically designed to probe forensic reasoning in egocentric safety scenarios. It comprises 12,000 unique evaluation samples, generated by pairing each of the 3,000 video clips with a QA chain governed by our proposed Hierarchical Reasoning Evaluation (HRE) protocol. Unlike standard benchmarks, HRE mandates a rigorous reasoning trajectory from initial feature anchoring to blind-spot deduction and intent inference, thereby enforcing logical consistency and penalizing shortcut-based predictions. Extensive evaluations of state-of-the-art LVLMs (e.g., Qwen3-VL, Gemini, VideoLLaMA 3) reveal a significant perception-reasoning decoupling: models often achieve high descriptive scores but exhibit notable fragility in causal reasoning and logical closure. Our work provides both a challenging dataset and a systematic evaluation framework to foster the development of logically robust video understanding systems.

Construction-safety models must handle concrete deployment risks, such as a worker standing near a scaffold edge without guardrails, rather than only recognize common objects in curated images. Yet real inspection archives are redundant, long-tailed, and collected across changing sites and months. We introduce SafeBuild-Bench, a metadata-driven benchmark for evaluating multimodal large language models on construction safety under realistic temporal and site variation. It is mined from 100K+ industrial image-text records and contains 3,314 task instances from over 3,000 expert-verified images, covering multiple-choice hazard identification and free-form hazard description. To make expert verification scalable, we develop GEMS, a graph-enhanced multimodal selection pipeline that combines a proxy-model confusion signal with graph-based diversity to identify informative candidates from redundant streams. On public instruction-tuning data, GEMS-selected subsets preserve robustness-oriented performance under small data budgets. On SafeBuild-Bench, current MLLMs remain far from reliable construction-safety understanding, with the best overall score near 60. We release the benchmark, evaluation scripts, and GEMS codebase at https://github.com/safebuild/gems.

Multi-agent systems improve capability through task decomposition and role specialization, but these same mechanisms introduce an important safety blind spot: a harmful objective can be fragmented into locally plausible subtasks, allowing malicious intent to evade detection by any single agent. This is a growing social-impact challenge: systems handling sensitive information or consequential tools can turn routine delegation into unauthorized disclosure or unsafe action. We argue that this failure mode is better understood as a semantic information-flow problem than as a single-turn prompt classification task. To address this, we propose SafeFlow, a defense framework for multi-agent systems that formalizes malicious cross-agent propagation as a semantic information-flow problem. SafeFlow attaches structured semantic taints to root requests, propagates them through a dynamic collaboration graph, and performs workflow-level validation to reconstruct the global risk context before irreversible actions are committed. Evaluated on four benchmarks spanning prompt injection, jailbreak-based unsafe tool use, risky code execution, and harmful web-agent behavior, SafeFlow reduces attack success rates compared to undefended baselines and external defenses while retaining high benign task completion and a high paired safe--harm success rate. Our findings show that multi-agent systems still lack mechanisms for preserving risk semantics across delegation boundaries. This gap can turn routine delegation into privacy harms or unsafe actions that affect people and organizations. SafeFlow keeps this risk visible throughout the workflow, before it results in harm.

Multi-modal large language models (MLLMs) integrate heterogeneous modalities through modality alignment and fusion, enabling stronger understanding and reasoning. However, this architectural shift reshapes the safety landscape of machine learning. Increased model complexity and cross-modal interactions give rise to novel threats, including compromised modality integration, modality misalignment, and fused safety risks, reflecting shifts in threat modeling beyond uni-modal assumptions. These shifts, in turn, impose new constraints on safety solutions not captured by existing frameworks rooted in uni-modal learning. Motivated by these challenges, this survey provides a systematic analysis of the evolving safety landscape of MLLMs. We first propose a multimodal grounded taxonomy of safety threats and analyze shifts in threat models, covering adversarial attacks, data poisoning, jailbreaks, and hallucinations. We then summarize updated safety assumptions and organize recent advances in MLLM safety strategies accordingly. Finally, we discuss open challenges and future directions to inform the development of more principled and scalable safety mechanisms for multimodal systems.

Jailbreak defenses are essential for protecting large language models (LLMs), but they can also introduce secondary costs that weaken model utility. We present a systematic study of these defense trade-offs along three dimensions: performance impact, over-refusal on benign inputs, and inference cost. Rather than treating defenses as a single class, we organize them by operational strategy and examine how different strategies correlate with different side-effect profiles. Across state-of-the-art defense methods, widely used benchmark datasets, and representative open-source LLMs, we find that defenses rarely improve downstream capability, but instead vary in how they trade safety gains against usability and efficiency. In particular, rule-based defenses best preserve task performance, highly conservative self-reflective defenses often increase over-refusal, and multi-round defenses incur the largest runtime overhead. These results provide both a benchmark for evaluating defense side effects and practical guidance for selecting defenses under deployment constraints.

Mainstream AI research emphasises capability growth and tolerates low failure rates when average-case performance is high. AI safety and alignment research has a different mission: to ensure that catastrophic failures never occur, under sparse evidence, adversarial dynamics, and fat-tailed risk. We argue that the two domains differ along two analytically independent axes---{\it capability profile}, demonstrating the absence of hazardous behaviours rather than the presence of positive capabilities, and {\it risk profile}, bounding worst-case outcomes under fat-tailed uncertainty rather than optimising average-case performance---and that mainstream epistemic practices are inadequate on both. Building on a structured synthesis grounded in a preregistered bibliometric baseline, we identify five cross-cutting gap dimensions in current alignment research, including the near-absence of institutionalised independent verification. To address these gaps, we propose {\sc ECAISA}, an Epistemic Code for AI Safety and Alignment comprising eight principles, a three-level scoring rubric, a four-level disclosure ladder that reconciles transparency with information-hazard and commercial-confidentiality constraints, a tiered applicability scheme, an information-hazard adjudication procedure, and seven anti-gaming mechanisms. {\sc ECAISA} does not certify that any AI system is safe; it constrains how safety-relevant research claims are documented, checked, and relied upon, with auditability rather than certification as its governance target.

A short fine-tuning run can undo the safety guards of an open-weight model---retraining a refusal-trained assistant to aid weapons development or produce hate speech. Preventing such harmful fine-tuning while retaining benign adaptability remains difficult: the only prior method with an explicit curvature certificate, spectral deformation, inflates curvature globally and thereby obstructs benign adaptation along with harmful adaptation. We propose HarmAlign, which applies function-preserving spectral deformation along a estimated contrastive activation subspace. We derive finite-sample bounds for the estimated subspace energy and the resulting local harmful-distribution curvature lower bound. A stability--progress dichotomy for constant-step gradient descent turns the certified curvature into conditional convergence-rate control. Empirically, within a fixed-architecture, finite-budget first-order threat model, HarmAlign blocks direct fine-tuning and three data- or objective-adaptive attacks across a hazardous-knowledge relearning setting and a harmful-assistance fine-tuning setting, while the protected benign tasks remain trainable. The block persists across the tested first-order optimizer variants over every attack checkpoint, and under out-of-distribution harmful fine-tuning, and it extends to important cases in our threat model: accidental safety degradation and emergent misalignment.

Runtime guardrails act before irreversible tool calls, but their guarantees depend on what policy state is representable, what a judge observes, and whether intervention changes future behavior. We separate three questions. First, relative to fixed oracle predicates, a deterministic gate enforces exactly the nonempty safety policies whose good prefixes its register model recognizes; policy nontriviality is undecidable with two decrementable counters but in PSPACE for a separable monotone fragment. Second, under a fixed exogenous law, Neyman-Pearson gives the exact false-block/miss frontier and conformal calibration gives a finite-sample marginal certificate, possibly via block-all. Third, once blocking changes future proposals, static scores and ungated trajectories need not identify the closed-loop frontier; a specified finite controlled model instead yields an occupancy program. Bounded representation attacks add a robustness margin, so benign calibration alone does not transfer. Experiments target these distinctions through static diagnostics, controlled-model enumeration, representation rewrites, and paired closed-loop reruns.

Recent advances have introduced speech-to-speech (S2S) conversational assistants capable of producing natural-sounding interactions, including non-verbal cues like tonality and mood. In the automotive domain, this enables intuitive and humanlike in-car dialogue experiences. However, integrating these end-to-end assistants limits architectural options for programmable domain-specific safeguards. This paper discusses two implementation approaches for S2S guardrails: transcript-based and tool-based. Through an empirical evaluation, we demonstrate that both strategies are insufficient for industrial deployment in most cases due to prohibitive latency (delaying each answer by 0 to 1.4 seconds even for computationally cheap checks) and technical impediments (like potentially non-deterministic tool call behavior). Finally, we outline open challenges for S2S guardrails in the automotive context.

More than a million people in the UK suffer from frailty or dementia, which severely compromise their ability to travel in urban environments. This paper presents SafeStep, an AI-driven travel system that assists elderly users with their journeys. At the core of SafeStep is a novel travel graph representation, which integrates route planning with predictive modelling. For each stage of a journey, the system (i) generates personalized failure scenarios using a combi-nation of LLMs and the Anticip8 behavioral prediction engine, (ii) proposes targeted interventions, and (iii) estimates the impact of interventions on out-come probabilities. This enables SafeStep to select interventions that maximize the likelihood of the person reaching their destination. SafeStep was evaluated through experiments on travel graph generation and a field study involving 26 real-world journeys. Results showed that combining Anticip8 for failure pre-diction with GPT-based models for intervention evaluation yields the most re-liable performance. User feedback indicated that SafeStep improves confidence and perceived safety during travel, although interface usability needs to be im-proved for the target demographic. In the future, we would like to improve and release SafeStep. The AI system that was developed for SafeStep could be ap-plied in other areas, such as mental health, career coaching and addiction treatment.

As Video Large Language Models are increasingly deployed in real-world applications, ensuring their safety alignment has become critical. Counterintuitively, we find that harmful videos paired with benign queries achieve higher attack success rates than the same videos paired with explicitly harmful queries. To understand the underlying mechanism of this vulnerability, we present V-DEAL, a three-level diagnostic framework that jointly analyzes this failure across model behaviour, understanding, and internal representations. By progressively ruling out perception failure and quantifying the model's internal refusal tendency, V-DEAL provides a new diagnostic perspective for analyzing the underlying mechanism of the observed vulnerability. We tested six Video LLMs on three public benchmarks and observed that models correctly recognize harmful video content with over 81% accuracy, yet the average attack success rate still reaches 48.33% under the condition pairing harmful videos with benign queries. Hidden-state analysis further shows that visual understanding activates a weaker refusal tendency than textual understanding. Furthermore, we introduce a prompt injection intervention method that reduces attack success rates by an average of 48.24 percentage points and achieves performance comparable to prior fine-tuning-based methods, providing an effective and practical means to address such safety risks in Video LLMs.

Almost every large language model that reaches a broad audience is quantized: trained in full precision, then compressed for efficiency. This step is assumed harmless and its safety is rarely re-checked. We find its principal side effect is increased bias that standard safety evaluation misses. Holding the model, its training, and the prompts fixed, a quantized model still refuses harmful requests, still avoids over-refusing benign prompts, and still selects the unbiased multiple-choice answer. Yet asked an open-ended question, the same model volunteers stereotypes in all eight languages we probe, in roughly one in four open-ended answers under an independent judge (~24% to ~27% across the compression ladder): it passes every standard check and still reaches users measurably more biased. The selective gap is a robust finding; whether open-ended bias further increases with compression is less certain, sensitive to the judge that scores it. We address both with \textbf{QuantiBias}, a benchmark that pairs a generative, multilingual stereotype probe with the refusal and multiple-choice controls that isolate open-ended generation, contrasts each build with and without reasoning, and rates the content severity of what it generates. Across two backbone models (Qwen and Gemma), a five-family screen, and eight benchmarks, quantizers allocate their extra precision by capability data that carries no bias-prevention signal, and reasoning before answering roughly halves the effect on some families while doing nothing on others. A quantized build must be re-evaluated for open-ended bias, not only on the short-form safeguards it already passes.

Aquatic self-reconfigurable robots must assemble into desired shapes while ensuring safe interactions among multiple agents. This paper proposes a hybrid framework that combines distributed Model Predictive Control (MPC) with Control Barrier Functions (CBFs) for multi-agent shape formation and reconfiguration. Given a desired shape and target assignment, a distributed MPC scheme, solved via the Alternating Direction Method of Multipliers (ADMM), computes coordinated trajectories through local optimization and information exchange. To ensure safety in real time, distributed CBF-based filters are applied to enforce inter-agent collision avoidance. The proposed approach leverages the predictive capabilities of MPC to mitigate local minima, while CBFs provide formal safety guarantees despite the nonconvexity of the underlying optimization problem. Simulation results with up to 25 agents and experimental validation with four physical robots demonstrate the effectiveness and scalability of the framework.

We propose a novel framework for computing rigorous bounds on the probability that a large language model (LLM) generates harmful output to a given prompt. We study a new application of the Clopper-Pearson confidence intervals to obtain probably approximately correct (PAC) bounds for this problem. As our main technical contribution, we propose an algorithm that leverages features in the latent space to prioritize exploring branches in the auto-regressive generation tree that are more likely to produce harmful outputs. Our approach in particular enables the efficient computation of useful lower bounds, even in scenarios where the true harm probability is extremely small, and crucially, the obtained lower bounds are sound, i.e., formally proven to be less than the actual harmfulness probability: our experimental results demonstrate the effectiveness of our method by computing non-trivial lower bounds on state-of-the-art LLMs. This study newly enables the evaluation and statistical certification of LLMs.