Safety Evaluation of VLAs

VLA: Vision-Language-Action Model

Overview

This field tests whether robots and driving agents can interpret instructions and act safely in interactive environments. Benchmarks use matched safe and unsafe scenarios, trajectory-level safety rules, counterfactual tests, and simulation-to-physical evaluation to separate safe behavior from task completion. Methods include adversarial red teaming, runtime action screening and abstention, semantic guards, robustness checks, and safety-aware training. Strong hazard recognition or task success often fails to ensure safe execution, leaving open challenges in cross-domain generalization, standardized metrics, and balancing safety with useful performance.

Latest papers

41 papers14 papers in the last four weeks, up 250% on the four weeks before. 0.1% of all new papers.

May 30, 2026

SafeVLA-Bench: A Benchmark for the Success-Safety Gap in Vision-Language-Action Models

Vision-language-action (VLA) benchmarks measure whether a policy completes a requested manipulation task, but binary success can hide safety violations along the trajectory: a policy may reach the goal while applying excessive contact, disturbing bystander objects, destabilizing a held object, or entering robot self-contact. We present SafeVLA-Bench, a post-hoc safety-evaluation framework for existing simulator-based VLA benchmarks that reveals violations missed by success-only evaluation. It encodes task-aware safety requirements as Signal Temporal Logic (STL) invariants with quantitative robustness semantics. Alongside native success, it reports the safety rate and the success-but-unsafe rate (SBU) used in prior safety evaluations, and introduces the Violation Severity Index (VSI), a bounded worst-violation depth score. We instantiate SafeVLA-Bench on LIBERO and RoboCasa-365, evaluating twenty-seven policy-benchmark entries across tabletop and kitchen manipulation tasks. High task success does not imply safe execution: the fifteen tabletop policies above 90% mean success still have 18-28% unsafe-episode rates, and 38-56% of successful RoboCasa-365 rollouts violate at least one active safety clause. A post-training case study further shows that SafeVLA-Bench can be used to improve policy safety. Project page: https://safevla.org
May 28, 2026

BOKBO (Best of K Bad Options): Calibrated Abstention for VLA Policies

Test-time scaling for vision-language-action (VLA) policies, methods such as RoboMonkey, SEAL, MG-Select, and V-GPS, samples K candidate action chunks at inference and executes the verifier-best. When all K candidates are unsafe, the system executes a violating action with no warning. We propose BOKBO, the first conformal abstention layer for K-sample VLA inference, providing finite-sample distribution-free guarantees on executed-violation rate. We provide both global and per-task (Mondrian) variants, with the per-task variant closing the conditional gap on the hardest tasks. Our analysis exposes a structural failure of policy-internal nonconformity scores under perturbation-based K-sampling: the base-policy confidence proxy and K-sample disagreement correlate at 0.98 with the action-noise hyperparameter σσ, while correlating at the noise floor with actual safety violations. We test the failure's scope by replicating the analysis under token-level temperature sampling and find the failure is mechanism-specific and partially mitigated under policy-stochasticity-based sampling. A learned violation predictor conditioned on semantic visual features and task identity supports tight calibration: at εε = 0.05 on libero_object_temp_x0.1 with OpenVLA-OFT, the conditional CRC bound holds on 86% of bootstrap splits with 78% coverage and 70% net task success. Mondrian-BOKBO raises the minimum per-task conditional hold fraction from 0.71 to 0.93. Results are stable across 5 training seeds, replicate within bootstrap noise on π0π_0-FAST, hold on libero_spatial_temp_x0.1 as a co-equal benchmark, and survive four within-suite distribution shifts. We additionally identify and correct a methodological pitfall: globally-set force thresholds well below expert-typical manipulation forces conflate unsafe behavior with normal manipulation, inflating violation rates by 5×5\times.
May 27, 2026

ReasonBreak: Probing Vulnerabilities in Reasoning-Enabled Vision-Language-Action Models for Autonomous Driving

Vision-Language-Action (VLA) models with integrated reasoning have been proposed for end-to-end autonomous driving, assuming a tight coupling between reasoning and trajectory generation. However, the robustness of such systems under realistic input perturbations remains largely unexplored. We show that these models are highly vulnerable to realistic input perturbations, achieving up to 89% attack success rate (ASR) on reasoning and up to 72% on trajectory manipulation in closed-loop simulation, leading to increased collision rates and degraded safety metrics. Using NVIDIA's recent Alpamayo models as representative industry-developed VLAs, we conduct the first systematic black-box study of reasoning-enabled VLA models under realistic textual input corruptions, evaluating their impact on reasoning and driving behavior. We introduce a reasoning-aware evaluation framework capturing both semantic and structural aspects of reasoning, along with safety-centric measures. We also introduce a benchmark for evaluating attacks and defenses on reasoning-trajectory interactions in autonomous driving. Our results highlight the need for rigorous evaluation and improved defenses to ensure the safety of reasoning-enabled VLA systems in autonomous driving.
May 21, 2026

Pre-VLA: Preemptive Runtime Verification for Reliable Vision-Language-Action and World-Model Rollouts

While large vision-language-action (VLA) models and generative world models (WM) have advanced long-horizon embodied intelligence, their practical deployment remains challenged by uncertainty in learning-based action generation. Low-quality actions may cause physical failures during execution or lead to misleading world-model rollouts with redundant rendering costs. To address this issue, we propose Pre-VLA, a unified runtime verification architecture that performs preemptive action validity assessment before physical execution or world-model imagination. Pre-VLA leverages an efficient multimodal backbone with modality-aware pooling and a lightweight dual-branch head to predict both safety confidence and critic-derived advantage scores for candidate action chunks. To handle severe class imbalance and unstable boundary decisions, we train Pre-VLA with a multi-task objective combining Focal classification, advantage regression, and soft-threshold calibration. During deployment, a dual-mode preemptive resampling scheduler filters low-quality actions and triggers adaptive resampling under a limited computation budget. Experiments on the LIBERO benchmark show that Pre-VLA improves the average closed-loop success rate across four suites from 30.79% to 37.62% over RynnVLA-002, reduces task execution steps, achieves 183.9 ms average forward verification time per action chunk, and mitigates error accumulation in world-model rollouts.
Apr 26, 2026

Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms

Vision-Language-Action (VLA) models are emerging as a unified substrate for embodied intelligence. This shift raises a new class of safety challenges, stemming from the embodied nature of VLA systems, including irreversible physical consequences, a multimodal attack surface across vision, language, and state, real-time latency constraints on defense, error propagation over long-horizon trajectories, and vulnerabilities in the data supply chain. Yet the literature remains fragmented across robotic learning, adversarial machine learning, AI alignment, and autonomous systems safety. This survey provides a unified and up-to-date overview of safety in Vision-Language-Action models. We organize the field along two parallel timing axes, attack timing (training-time vs. inference-time and defense timing (training-time vs. inference-time, linking each class of threat to the stage at which it can be mitigated. We first define the scope of VLA safety, distinguishing it from text-only LLM safety and classical robotic safety, and review the foundations of VLA models, including architectures, training paradigms, and inference mechanisms. We then examine the literature through four lenses: Attacks, Defenses, Evaluation, and Deployment. We survey training-time threats such as data poisoning and backdoors, as well as inference-time attacks including adversarial patches, cross-modal perturbations, semantic jailbreaks, and freezing attacks. We review training-time and runtime defenses, analyze existing benchmarks and metrics, and discuss safety challenges across six deployment domains. Finally, we highlight key open problems, including certified robustness for embodied trajectories, physically realizable defenses, safety-aware training, unified runtime safety architectures, and standardized evaluation.
Apr 24, 2026

RedVLA: Physical Red Teaming for Vision-Language-Action Models

The real-world deployment of Vision-Language-Action (VLA) models remains limited by the risk of unpredictable and irreversible physical harm. However, we currently lack effective mechanisms to proactively detect these physical safety risks before deployment. To address this gap, we propose RedVLA, the first red teaming framework for physical safety in VLA models. We systematically uncover unsafe behaviors through a two-stage process: (I) Risk Scenario Synthesis constructs a valid and task-feasible initial risk scene. Specifically, it identifies critical interaction regions from benign trajectories and positions the risk factor within these regions, aiming to entangle it with the VLA's execution flow and elicit a target unsafe behavior. (II) Risk Amplification ensures stable elicitation across heterogeneous models. It iteratively refines the risk factor state through gradient-free optimization guided by trajectory features. Experiments on six representative VLA models show that RedVLA uncovers diverse unsafe behaviors and achieves the ASR up to 95.5% within 10 optimization iterations. To mitigate these risks, we further propose SimpleVLA-Guard, a lightweight safety guard built from RedVLA-generated data. Our data, assets, and code are available here.
Apr 23, 2026

How VLAs (Really) Work In Open-World Environments

Vision-language-action models (VLAs) have been extensively used in robotics applications, achieving great success in various manipulation problems. More recently, VLAs have been used in long-horizon tasks and evaluated on benchmarks, such as BEHAVIOR1K (B1K), for solving complex household chores. The common metric for measuring progress in such benchmarks is success rate or partial score based on satisfaction of progress-agnostic criteria, meaning only the final states of the objects are considered, regardless of the events that lead to such states. In this paper, we argue that using such evaluation protocols say little about safety aspects of operation and can potentially exaggerate reported performance, undermining core challenges for future real-world deployment. To this end, we conduct a thorough analysis of state-of-the-art models on the B1K Challenge and evaluate policies in terms of robustness via reproducibility and consistency of performance, safety aspects of policies operations, task awareness, and key elements leading to the incompletion of tasks. We then propose evaluation protocols to capture safety violations to better measure the true performance of the policies in more complex and interactive scenarios. At the end, we discuss the limitations of the existing VLAs and motivate future research.
Apr 21, 2026

SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models

Multimodal Large Language Models are increasingly adopted as autonomous agents in interactive environments, yet their ability to proactively address safety hazards remains insufficient. We introduce SafetyALFRED, built upon the embodied agent benchmark ALFRED, augmented with six categories of real-world kitchen hazards. While existing safety evaluations focus on hazard recognition through disembodied question answering (QA) settings, we evaluate eleven state-of-the-art models from the Qwen, Gemma, and Gemini families on not only hazard recognition, but also active risk mitigation through embodied planning. Our experimental results reveal a significant alignment gap: while models can accurately recognize hazards in QA settings, average mitigation success rates for these hazards are low in comparison. Our findings demonstrate that static evaluations through QA are insufficient for physical safety, thus we advocate for a paradigm shift toward benchmarks that prioritize corrective actions in embodied contexts. We open-source our code and dataset under https://github.com/sled-group/SafetyALFRED.git
Apr 14, 2026

HazardArena: Evaluating Semantic Safety in Vision-Language-Action Models

Vision-Language-Action (VLA) models inherit rich world knowledge from vision-language backbones and acquire executable skills from action demonstrations. Yet current evaluations primarily measure task completion, leaving the semantic safety of learned action policies underexplored. This gap creates a critical vulnerability: a policy may execute the intended action correctly while producing unsafe outcomes when the surrounding visual-linguistic context changes. We present HazardArena, a benchmark for stress-testing semantic safety in VLA systems. Its core design is a set of safe/unsafe twin scenarios: paired environments with matched objects, layouts, and action requirements, but different semantic risk contexts. This controlled contrast isolates safety judgment from motor capability and directly tests whether a VLA can recognize when an otherwise valid action becomes hazardous. HazardArena includes over 2,000 assets and 51 risk-sensitive tasks across seven safety categories grounded in robotic safety standards. Across four representative VLA backbones, we observe a consistent and alarming pattern: safe-only fine-tuning improves benign task success while also increasing hazardous execution on matched unsafe scenarios. Physical-world experiments confirm that this failure transfers beyond simulation. These results show that stronger action execution does not imply safer behavior, and motivate semantic-risk-aware evaluation and enforcement as first-class requirements for real-world VLA deployment. Code released at https://github.com/HazardArena-Team/HazardArena ; updated code availability information.
Apr 7, 2026

Uncovering Linguistic Fragility in Vision-Language-Action Models via Diversity-Aware Red Teaming

Vision-Language-Action (VLA) models have achieved remarkable success in robotic manipulation. However, their robustness to linguistic nuances remains a critical, under-explored safety concern, posing a significant safety risk to real-world deployment. Red teaming, or identifying environmental scenarios that elicit catastrophic behaviors, is an important step in ensuring the safe deployment of embodied AI agents. Reinforcement learning (RL) has emerged as a promising approach in automated red teaming that aims to uncover these vulnerabilities. However, standard RL-based adversaries often suffer from severe mode collapse due to their reward-maximizing nature, which tends to converge to a narrow set of trivial or repetitive failure patterns, failing to reveal the comprehensive landscape of meaningful risks. To bridge this gap, we propose a novel Diversity-Aware Embodied Red Teaming (DAERT) framework, to expose the vulnerabilities of VLAs against linguistic variations. Our design is based on evaluating a uniform policy, which is able to generate a diverse set of challenging instructions while ensuring its attack effectiveness, measured by execution failures in a physical simulator. We conduct extensive experiments across different robotic benchmarks against two state-of-the-art VLAs, including π0π_0 and OpenVLA. Our method consistently discovers a wider range of more effective adversarial instructions that reduce the average task success rate from 93.33% to 5.85%, demonstrating a scalable approach to stress-testing VLA agents and exposing critical safety blind spots before real-world deployment.
Mar 16, 2026

Safety Case Patterns for VLA-based driving systems: Insights from SimLingo

Vision-Language-Action (VLA)-based driving systems represent a significant paradigm shift in autonomous driving since, by combining traffic scene understanding, linguistic interpretation, and action generation, these systems enable more flexible, adaptive, and instruction-responsive driving behaviors. However, despite their growing adoption and potential to support socially responsible autonomous driving as well as understanding high-level human instructions, VLA-based driving systems may exhibit new types of hazardous behaviors. For instance, the integration of open-ended natural language inputs (e.g., user or navigation instructions) into the multimodal control loop may lead to unpredictable and unsafe behaviors that could endanger vehicle occupants and pedestrians. Hence, assuring the safety of these systems is crucial to help build trust in their operations. To support this, we propose a novel safety case design approach called RAISE. Our approach introduces novel patterns tailored to instruction-based driving systems such as VLA-based driving systems, an extension of Hazard Analysis and Risk Assessment (HARA) detailing safe scenarios and their outcomes, and a design technique to create the safety cases of VLA-based driving systems. A case study on SimLingo illustrates how our approach can be used to construct rigorous, evidence-based safety claims for this emerging class of autonomous driving systems.