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

This paper introduces a novel framework, the Reasoning Safety Monitor, to detect and prevent logical inconsistencies and adversarial manipulations within the internal reasoning steps of large language…

The paper introduces Safety Bottleneck Regularization (SBR), a novel defense mechanism that anchors LLM safety by constraining the unembedding layer, effectively preventing harmful fine-tuning (HFT) e…

The paper introduces Opir, an efficient family of encoder-based multi-task guardrail models that provides competitive safety classification performance across various tasks while maintaining a signifi…

The paper introduces SecureBreak, a manually annotated, safety-oriented dataset designed to help detect harmful outputs from large language models (LLMs) that bypass existing security alignments.

The paper proposes AHV-D&S, a novel training-free inference-time safeguard that detects and suppresses risky content in Diffusion Transformers (DiTs) by quantifying token sensitivity across attention…

The paper introduces SkillReact, a framework that measures compositional risk in agent skill ecosystems, finding that even if individual skills are safe, their combination can create significant, unad…

The paper introduces SkillReact, a framework that measures compositional risk in agent skill ecosystems, finding that even if individual skills are safe, their combination can create significant, expl…

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 proposes DMN, a compositional jailbreak framework that utilizes distributed instructions, multimodal evidence, and a number chain task across multiple images to significantly enhance the att…

The paper proposes a novel zeroth-order optimization framework to enhance the robustness of LLM safety alignment, showing that few refinement steps can significantly improve safety while maintaining u…

The paper introduces Compositional Semantic Fingerprinting (CSF), a black-box method that allows IP owners to attribute fine-tuned text-to-image models to their protected lineages using only query acc…

The paper introduces FoodGuardBench, a comprehensive benchmark and a specialized guardrail model (FoodGuard-4B) to rigorously test and mitigate the severe food safety risks posed by large language mod…

The paper introduces EditRisk-Bench, a novel benchmark designed to systematically evaluate the safety risks and downstream reasoning corruption caused by malicious knowledge editing in large language…

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

The paper introduces TrojanMerge, a framework demonstrating that model merging can be exploited to systematically compromise the safety alignment of multiple individually safe LLMs.

The paper proposes SafeDIG, a robust safety steering framework that adapts Diffusion Transformers for text-to-image generation by treating safety control as position-aware sparse feature transfer, ens…

The EvoSafety framework enhances LLM safety by externalizing attack and defense mechanisms, enabling persistent, transferable, and model-agnostic robustness against adversarial prompts.