The paper introduces AutoMIA, a novel framework that uses LLM agents to automate the discovery and implementation of Membership Inference Attacks (MIAs), achieving state-of-the-art performance by syst…

The paper introduces RoboJailBench, the first standardized evaluation framework for assessing adversarial jailbreak attacks and defenses in embodied AI systems like robots.

The paper proposes Continuous Reasoning for Vision-Language-Action (VLA) models, arguing that effective reasoning must be a shared, verifiable internal latent space rather than discrete text tokens, l…

This paper presents a black-box membership inference attack (MIA) against Video Large Language Models (VideoLLMs), demonstrating that they are vulnerable by analyzing generation behavior across varyin…

The paper proposes a novel attack paradigm demonstrating how compromising a single robot in an LLM-controlled multi-robot system can rapidly propagate malicious intent to cause coordinated unsafe acti…

This paper introduces TRAP, an adversarial attack that demonstrates how physical patches can hijack the Chain-of-Thought (CoT) reasoning process in Vision-Language-Action (VLA) models, forcing them to…

VISUALTHINK-VLA introduces a visual intermediate-reasoning framework that guides action prediction using compact visual evidence, achieving high accuracy and significantly low latency for real-time Vi…

This survey provides a comprehensive taxonomy and vulnerability-centric analysis of adversarial attacks targeting Multimodal Large Language Models (MLLMs), offering an explanatory framework for enhanc…

This paper conducts a structured ablation study using a unified threat model to evaluate how various system factors (like model architecture and retrieval configuration) influence different types of p…

This survey provides a comprehensive, structured review of safety research in Embodied AI, analyzing attacks and defenses across the entire embodied pipeline to guide the development of safe, robust,…

This paper demonstrates that reasoning-enabled Vision-Language-Action (VLA) models for autonomous driving are highly vulnerable to realistic input perturbations, significantly compromising both reason…

The paper evaluates the adversarial robustness of two open-source Vision-Language Models (LLaVA and Qwen2.5-VL) in a simulated e-commerce environment, finding that while LLaVA is vulnerable to gradien…

The paper proposes Multi-Recall Memory MIA (MRMMIA), a unified attack framework to test for privacy leakage by determining if a candidate memory unit belongs to a chat agent's private memory store.

VLA-Trace is a diagnostic framework that analyzes Vision-Language-Action (VLA) models by tracing their internal representations and external behaviors, revealing that while these models are good at vi…

The paper introduces a novel, transferable learned attack (LT-MIA) that detects a universal 'signature of memorization' in language models, achieving high accuracy across diverse model architectures (…

The paper introduces SpatialAct, a challenging benchmark that reveals a significant 'reasoning-to-action gap,' showing that current VLMs struggle to maintain coherent spatial understanding and perform…

AutoMIA introduces an agentic framework that automates the process of Membership Inference Attacks (MIAs) by self-exploring the attack space, achieving state-of-the-art performance without manual feat…

The paper introduces Evidence-Carrying Agents (ECA) to prevent multimodal agents from executing privileged actions based on unsupported or hallucinated perceptual claims, achieving near-zero unsafe ex…

The paper introduces Session Risk Memory (SRM), a lightweight module that enhances per-action authorization gates with trajectory-level risk assessment, significantly improving detection of distribute…

The paper demonstrates that adversarial examples can be used to manipulate Vision-Language Models (VLMs) into confidently providing authoritative but incorrect information, a process termed 'AI author…