{"total":73,"rows":[{"id":"2510.03827","title":"LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond Memorization","created":"2025-10-04","cited_by_count":179,"area":"vla"},{"id":"2510.07077","title":"Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications","created":"2025-10-08","cited_by_count":84,"area":"mllm"},{"id":"2505.04769","title":"Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challenges","created":"2025-05-07","cited_by_count":74,"area":"mllm"},{"id":"2502.05206","title":"Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety","created":"2025-02-02","cited_by_count":67,"area":"mllm"},{"id":"2509.19012","title":"Pure Vision Language Action (VLA) Models: A Comprehensive Survey","created":"2025-09-23","cited_by_count":49,"area":"mllm"},{"id":"2505.16640","title":"BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization","created":"2025-05-22","cited_by_count":38,"area":"vla"},{"id":"2507.10672","title":"Vision Language Action Models in Robotic Manipulation: A Systematic Review","created":"2025-07-14","cited_by_count":38,"area":"vla"},{"id":"2509.18953","title":"Eva-VLA: Evaluating Vision-Language-Action Models' Robustness Under Real-World Physical Variations","created":"2025-09-23","cited_by_count":24,"area":"vla"},{"id":"2510.13237","title":"Model-agnostic Adversarial Attack and Defense for Vision-Language-Action Models","created":"2025-10-15","cited_by_count":22,"area":"vla"},{"id":"2509.19870","title":"FreezeVLA: Action-Freezing Attacks against Vision-Language-Action Models","created":"2025-09-24","cited_by_count":21,"area":"vla"},{"id":"2511.16203","title":"When Alignment Fails: Multimodal Adversarial Attacks on Vision-Language-Action Models","created":"2025-11-20","cited_by_count":20,"area":"vla"},{"id":"2510.09269","title":"Goal-oriented Backdoor Attack against Vision-Language-Action Models via Physical Objects","created":"2025-10-10","cited_by_count":17,"area":"vla"},{"id":"2601.06748","title":"On-the-Fly VLA Adaptation via Test-Time Reinforcement Learning","created":"2026-01-11","cited_by_count":14,"area":"vla"},{"id":"2511.21192","title":"When Robots Obey the Patch: Universal Transferable Patch Attacks on Vision-Language-Action Models","created":"2025-11-26","cited_by_count":13,"area":"vla"},{"id":"2604.23775","title":"Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms","created":"2026-04-26","cited_by_count":13,"area":"vla"},{"id":"2511.12149","title":"AttackVLA: Benchmarking Adversarial and Backdoor Attacks on Vision-Language-Action Models","created":"2025-11-15","cited_by_count":12,"area":"vla"},{"id":"2511.21663","title":"Attention-Guided Patch-Wise Sparse Adversarial Attacks on Vision-Language-Action Models","created":"2025-11-26","cited_by_count":11,"area":"vla"},{"id":"2604.10055","title":"STRONG-VLA: Decoupled Robustness Learning for Vision-Language-Action Models under Multimodal Perturbations","created":"2026-04-11","cited_by_count":10,"area":"vla"},{"id":"2511.10008","title":"Phantom Menace: Exploring and Enhancing the Robustness of VLA Models Against Physical Sensor Attacks","created":"2025-11-13","cited_by_count":9,"area":"vla"},{"id":"2601.04266","title":"State Backdoor: Towards Stealthy Real-world Poisoning Attack on Vision-Language-Action Model in State Space","created":"2026-01-07","cited_by_count":9,"area":"vla"},{"id":"2505.03500","title":"VLAs are Confined yet Capable of Generalizing to Novel Instructions","created":"2025-05-06","cited_by_count":8,"area":"vla"},{"id":"2604.12447","title":"HazardArena: Evaluating Semantic Safety in Vision-Language-Action Models","created":"2026-04-14","cited_by_count":8,"area":"vla"},{"id":"2604.05498","title":"JailWAM: Jailbreaking World Action Models in Robot Control","created":"2026-04-07","cited_by_count":6,"area":"wm"},{"id":"2509.00117","title":"Embodied AI: Emerging Risks and Opportunities for Policy Action","created":"2025-08-28","cited_by_count":5,"area":null},{"id":"2603.23117","title":"TRAP: Hijacking VLA CoT-Reasoning via Adversarial Patches","created":"2026-03-24","cited_by_count":5,"area":"lr"},{"id":"2508.19445","title":"On Surjectivity of Neural Networks: Can you elicit any behavior from your model?","created":"2025-08-26","cited_by_count":4,"area":null},{"id":"2510.07067","title":"Bring the Apple, Not the Sofa: Impact of Irrelevant Context in Embodied AI Commands on VLA Models","created":"2025-10-08","cited_by_count":4,"area":"vla"},{"id":"2605.28083","title":"VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking","created":"2026-05-27","cited_by_count":4,"area":"vla"},{"id":"2606.03556","title":"Partially Observable Adversarial Patch Attacks on Vision-Language-Action Models in Robotics","created":"2026-06-02","cited_by_count":4,"area":"vla"},{"id":"2509.03383","title":"ANNIE: Be Careful of Your Robots","created":"2025-09-03","cited_by_count":3,"area":"vla"},{"id":"2605.19678","title":"RoVLA: Multi-Consistency Constraints for Robust Vision-Language-Action Models","created":"2026-05-19","cited_by_count":3,"area":"vla"},{"id":"2505.23266","title":"Disrupting Vision-Language Model-Driven Navigation Services via Adversarial Object Fusion","created":"2025-05-29","cited_by_count":2,"area":"mllm"},{"id":"2603.16960","title":"Adversarial attacks against Modern Vision-Language Models","created":"2026-03-17","cited_by_count":2,"area":"mllm"},{"id":"2603.24935","title":"SABER: A Stealthy Agentic Black-Box Attack Framework for Vision-Language-Action Models","created":"2026-03-26","cited_by_count":2,"area":"vla"},{"id":"2605.09005","title":"Towards Backdoor-Based Ownership Verification for Vision-Language-Action Models","created":"2026-05-09","cited_by_count":2,"area":"vla"},{"id":"2606.10501","title":"Uncovering Vulnerability of Vision-Language-Action Models under Joint-Level Physical Faults","created":"2026-06-09","cited_by_count":2,"area":"vla"},{"id":"2606.15165","title":"VLALeaks: Membership Inference Attacks against Vision-Language-Action Models","created":"2026-06-13","cited_by_count":2,"area":"vla"},{"id":"2608.05715","title":"Hijacking Robots with a Piece of Paper: A Systematic Study of Physical Prompt Injection in VLM-Controlled Robots","created":"2026-08-06","cited_by_count":2,"area":"mllm"},{"id":"2504.17070","title":"MuTRAP: Multi-trigger Trojans Attacking Robot Task Planning Systems","created":"2025-04-23","cited_by_count":1,"area":null},{"id":"2505.09731","title":"Unfettered Forceful Skill Acquisition with Physical Reasoning and Coordinate Frame Labeling","created":"2025-05-14","cited_by_count":1,"area":"lr"},{"id":"2509.02163","title":"Enhancing Reliability in LLM-Integrated Robotic Systems: A Unified Approach to Security and Safety","created":"2025-09-02","cited_by_count":1,"area":null},{"id":"2511.04970","title":"Learning Fourier shapes to probe the geometric world of deep neural networks","created":"2025-11-07","cited_by_count":1,"area":null},{"id":"2604.09651","title":"FlowHijack: A Dynamics-Aware Backdoor Attack on Flow-Matching Vision-Language-Action Models","created":"2026-03-30","cited_by_count":1,"area":"vla"},{"id":"2604.22591","title":"RedVLA: Physical Red Teaming for Vision-Language-Action Models","created":"2026-04-24","cited_by_count":1,"area":"vla"},{"id":"2605.25889","title":"Capability and Robustness Cannot Both Be Free: An Information-Theoretic Bound for Vision-Language-Action Models","created":"2026-05-25","cited_by_count":1,"area":"vla"},{"id":"2607.12406","title":"Isolation as a First-Class Principle for LLM-Agent System Safety: Concepts, Taxonomy, Challenges and Future Directions","created":"2026-07-14","cited_by_count":1,"area":"agents"},{"id":"2608.01573","title":"Uncovering and Mitigating Positional Blind Spots in Vision-Language-Action Models","created":"2026-08-03","cited_by_count":1,"area":"vla"},{"id":"2608.03207","title":"DRIFT: Derailing Denoising Trajectories of Flow-Matching VLAs with Adversarial Patch Attack","created":"2026-08-04","cited_by_count":1,"area":"vla"},{"id":"2608.03231","title":"Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking","created":"2026-08-04","cited_by_count":1,"area":"vla"},{"id":"2608.13453","title":"UniTexture: Cross-Task Universal Adversarial Textures for Vision-Language-Action Models","created":"2026-08-13","cited_by_count":1,"area":"vla"},{"id":"2505.18792","title":"On the Dual-Use Dilemma in Physical Reasoning and Force","created":"2025-05-24","cited_by_count":0,"area":"lr"},{"id":"2512.06387","title":"Beyond Model Jailbreak: Systematic Dissection of the \"Ten DeadlySins\" in Embodied Intelligence","created":"2025-12-06","cited_by_count":0,"area":"safety"},{"id":"2601.06464","title":"On the Adversarial Robustness of 3D Large Vision-Language Models","created":"2026-01-10","cited_by_count":0,"area":"mllm"},{"id":"2605.07088","title":"Membership Inference Attacks on Vision-Language-Action Models","created":"2026-05-08","cited_by_count":0,"area":"safety"},{"id":"2605.18593","title":"Not What You Asked For: Typographic Attacks in Household Robot Manipulation","created":"2026-05-18","cited_by_count":0,"area":"mllm"},{"id":"2605.29114","title":"ReasonBreak: Probing Vulnerabilities in Reasoning-Enabled Vision-Language-Action Models for Autonomous Driving","created":"2026-05-27","cited_by_count":0,"area":"vla"},{"id":"2606.10371","title":"Test-time Adversarial Takeover: A Real-time Hijacking Interface against Robotic Diffusion Policies","created":"2026-06-09","cited_by_count":0,"area":"diffusion"},{"id":"2606.12978","title":"Trajectory-Level Redirection Attacks on Vision-Language-Action Models","created":"2026-06-11","cited_by_count":0,"area":"vla"},{"id":"2606.19897","title":"One-to-Two Acting: A Novel Framework for Single-arm Agent Action Expansion to Dual Arms","created":"2026-06-18","cited_by_count":0,"area":"agents"},{"id":"2607.17786","title":"Reasoning as a Double-Edged Sword: Architecture and Cross-Stage Robustness in Vision-Language-Action Models","created":"2026-07-20","cited_by_count":0,"area":"lr"},{"id":"2608.01028","title":"VLAGuard: A Framework for Evaluating and Mitigating Physical Attention Hijacking in Vision-Language-Action Robots within Wireless Sensor Networks","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.20791","title":"CertVLA: Certified Defense against Physical Visual Attacks for Vision-Language-Action Models","created":"2026-08-21","cited_by_count":0,"area":"vla"},{"id":"2608.26578","title":"TrapVLA: Trapping Vision-Language-Action Models in Configured Failure Modes","created":"2026-08-27","cited_by_count":0,"area":"vla"},{"id":"2609.19669","title":"Beyond Patch Removal: Persistent Adversarial Effects in Vision-Language-Action Policies","created":"2026-09-17","cited_by_count":0,"area":"vla"},{"id":"2609.22293","title":"Validating, Not Sampling: Region-Level Robustness of Vision-Language and Vision-Language-Action Models","created":"2026-09-14","cited_by_count":0,"area":"mllm"},{"id":"2609.27847","title":"Security and Privacy in Large-Model-Driven Embodied Agents: Attacks, Defenses, and Future Directions","created":"2026-08-19","cited_by_count":0,"area":"agents"},{"id":"2609.32550","title":"Are Vision-Language-Action Models Robust to One-Step Observation Perturbations?","created":"2026-09-26","cited_by_count":0,"area":"vla"},{"id":"2609.33707","title":"Does Adversarial Training Improve Generalization in Multi-View VLAs? Revealing and Mitigating View Collapse","created":"2026-09-27","cited_by_count":0,"area":"mllm"},{"id":"2609.36518","title":"LIBERO-MAX: Do Robot Policies Adapt When the World Changes?","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39178","title":"Exploiting Vulnerabilities: Universal Adversarial Attacks on Vision-Language-Action Models in Robotics","created":"2026-09-30","cited_by_count":0,"area":"vla"},{"id":"2610.03498","title":"Detect and Suppress: A Mechanistic Defense against Adversarial Patches in VLA Models","created":"2026-10-02","cited_by_count":0,"area":"vla"},{"id":"2610.06814","title":"TAPDreamer: Transferable Adversarial Patches for World Action Models","created":"2026-10-05","cited_by_count":0,"area":"wm"},{"id":"2610.15343","title":"Across Viewpoints and Time: Trajectory-Generalizable Physical Attacks on World Models and Video Understanding Models","created":"2026-10-11","cited_by_count":0,"area":"wm"}],"next_cursor":null}