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…

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 introduces ImageProtector, a user-side method that embeds an imperceptible perturbation into images to prevent Multi-modal Large Language Models (MLLMs) from analyzing and extracting sensiti…

This paper addresses the vulnerability of existing LLM safety monitors to adaptive attackers and proposes activation watermarking, a technique that significantly improves detection robustness against…

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 Multi-Clip Video (MCV) SafetyBench, a dataset demonstrating that the vulnerability of Multimodal Large Language Models (MLLMs) to jailbreaking increases with the diversity and num…

The paper proposes a general-purpose pipeline to train automated red teaming models capable of generating attacks for arbitrary adversarial goals, overcoming the limitations of current methods that ar…

The paper introduces Auto-ART, a comprehensive open-source framework that provides structured meta-analysis and automated testing for adversarial robustness, revealing significant gaps in current ML s…

The paper evaluates four RAG architectures under knowledge base poisoning, demonstrating that advanced architectures significantly improve robustness against adversarial contradictions, localizing the…

This paper introduces ComicJailbreak, a new benchmark demonstrating that structured visual narratives can effectively jailbreak Multimodal Large Language Models (MLLMs), requiring new safety alignment…

The paper introduces a dual-dimension evaluation for universal adversarial attacks on Vision-Language Models (VLMs), demonstrating that high reported attack success rates significantly overestimate th…

The paper demonstrates that using advanced AI agents in an autoresearch loop can discover novel and highly effective adversarial attack algorithms, significantly advancing the state-of-the-art for jai…

The paper proposes an end-to-end forensic pipeline using steganographic attribution and multimodal harm detection to reliably trace and attribute harmful misuse of AI-generated imagery on social platf…

This paper presents the first systematic study of membership inference attacks (MIAs) against Vision-Language-Action (VLA) models, demonstrating that these models are highly vulnerable to privacy brea…

The paper proposes a unified closed-loop threat taxonomy to systematically analyze and defend foundation models by explicitly framing the bidirectional security interactions between data and models.

The paper identifies a critical vulnerability, the Camouflage Detection Gap (CDG), where standard LLM injection detectors fail dramatically when malicious payloads mimic the target domain's language a…

The paper identifies the Misattribution Gap, showing that memory-layer attacks (Semantic Norm Drift) can mimic model failure in multi-agent AI systems, and proposes novel detection and mitigation tech…

The paper demonstrates that combining outputs from multiple large language models (LLMs) effectively cancels out statistical watermarks, revealing a fundamental vulnerability in current AI text detect…

The paper argues that current AI content watermarking benchmarks fail to test for bias across different languages, cultures, and demographics, proposing a new set of evaluation standards to ensure fai…

The paper introduces CrossMPI, a novel cross-modal prompt injection attack that uses image-only perturbations to steer the interpretation of both textual and visual inputs in Large Vision-Language Mod…