The paper proposes a novel cross-modal backdoor attack that exploits the vulnerability of lightweight connectors in multimodal LLMs, demonstrating high attack success rates across different modalities…

The paper analyzes that while multimodal large language models (MLLMs) offer superior semantic understanding for image generation, this enhanced capability significantly increases safety risks, partic…

The paper analyzes LLM vulnerability detection using mechanistic interpretability, finding that models primarily rely on safety detectors rather than direct vulnerability signature recognition.

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…

The paper compares two sparse autoencoder architectures, finding that Differential SAEs (Diff-SAE) significantly outperform Crosscoders in isolating backdoor-related features in language models.

This paper introduces the first backdoor attacks against VLM-based scanpath prediction, demonstrating variable-output attacks that evade detection and survive deployment on edge devices.

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 proposes Hydra, a framework to stabilize and control the injection of multiple, conflicting backdoor triggers into text-to-image diffusion models, ensuring high attack reliability while main…

The paper conducts an interpretability-driven safety audit of eight state-of-the-art LLMs, demonstrating that while interpretability-based steering is a powerful auditing tool, model robustness varies…

The paper introduces Distributed Semantic Recomposition (DSR), a novel cross-modal jailbreaking framework that bypasses existing safety filters by decomposing harmful intent into benign input componen…

The paper introduces Hidden Ads, a novel backdoor attack for Vision-Language Models (VLMs) that injects unauthorized advertisements by exploiting natural, recommendation-seeking user behaviors, mainta…

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…

This paper introduces the concept of Safety Geometry Collapse, demonstrating that multimodal inputs degrade the safety separation of LLMs, and proposes ReGap, a training-free method that adaptively co…

The paper introduces BadDLM, a unified framework that demonstrates a new class of backdoor vulnerabilities in Diffusion Language Models (DLMs) by exploiting their forward masking process across divers…

The paper introduces Critical-CoT, a novel two-stage fine-tuning defense framework that equips LLMs with critical thinking abilities to detect and reject malicious reasoning steps introduced by advanc…

This paper provides a systematic, lifecycle-based framework for analyzing security threats and defenses across the entire fine-tuning process of LLMs, revealing that attack effectiveness is highly mod…

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…

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 proposes a novel Text-Guided Backdoor (TGB) attack that uses common words in text descriptions as stealthy triggers for multimodal models, enhancing practicality and controllability.

The paper investigates how various fine-tuning methods can be used both to intentionally misalign and subsequently realign large language models (LLMs), revealing distinct strengths for attack and def…