The paper introduces MT-JailBench, a modular framework for evaluating multi-turn jailbreaks, demonstrating that controlling experimental components like prompt generation and resource budgets is cruci…

The paper investigates multimodal jailbreak robustness across various reasoning paradigms and finds that explicit image-tool interaction significantly improves safety by shifting the model's internal…

The paper investigates multimodal jailbreak robustness across various reasoning paradigms and finds that explicit image-tool interaction significantly improves safety by guiding the model's internal r…

This paper systematically analyzes the interaction of multiple weak jailbreak attacks (mutators) applied sequentially to LLMs, finding that most combinations fail due to destructive interference, reve…

The paper proposes SRTJ, a Self-Evolving Rule-Driven Training-Free Jailbreak framework that systematically discovers and refines attack strategies using rule composition and feedback to achieve robust…

The paper proposes TriageFuzz, a token-aware fuzzing framework that significantly reduces the number of queries needed to jailbreak LLMs while maintaining high attack success rates.

The paper introduces EvoJail, an automated multi-objective evolutionary framework that systematically discovers diverse and effective long-tail jailbreak attacks against LLMs by optimizing for attack…

This paper addresses the lack of systematic infrastructure for evaluating jailbreak attacks by introducing a large-scale dataset, an automated generation method, and a continuous evaluation metric tha…

This paper introduces Security Cube, a comprehensive, multi-dimensional framework for evaluating LLM robustness against jailbreak attacks, providing a systematic taxonomy and benchmark analysis of exi…

The paper introduces Babel, an efficient black-box attack framework that systematically exploits intrinsic safety gaps in LLMs by optimizing text obfuscation sampling, achieving state-of-the-art jailb…

TEMPLATEFUZZ is a fine-grained fuzzing framework that systematically tests chat templates to find vulnerabilities in LLMs, achieving high jailbreak success rates with minimal performance degradation.

This paper introduces the 'wide-net-casting' jailbreak scenario, demonstrating that querying a group of large language models can expose significant, previously overlooked safety risks, with a novel m…

D-Judge introduces a semantics-preserving output rewriting defense that disrupts multi-turn jailbreak attacks by misaligning the feedback signal used by an attacker's judge model.

The paper proposes a novel pre-model safeguard that uses small draft models (SLMs) to predict the safety of prompts, significantly reducing false-negative rates while maintaining low computational ove…

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 proposes TRACE, a novel agentic jailbreaking framework that successfully bypasses safety mechanisms of advanced LLM agents by decomposing malicious tasks and disguising harmful subtasks with…

This paper introduces a novel Function Hijacking Attack (FHA) that manipulates the tool selection process of agentic models, demonstrating a robust and context-agnostic threat to function calling LLMs…

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 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 an embedding disruption method to re-activate and strengthen built-in safeguards within LLMs, effectively detecting and defending against sophisticated jailbreak attacks.