The paper introduces THREAT, a novel reasoning-driven framework that efficiently discovers highly effective and targeted jailbreak prompts for LLMs, revealing previously unknown safety vulnerabilities…

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.

The paper proposes Ellipsoid Control, a white-list defense mechanism that uses benign data geometry to constrain model updates, thereby enhancing jailbreak safety while preserving the utility of harml…

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 mitigating the progressive degradation of safety in language models caused by many-shot jailbreak attacks by appending a single, fixed safety demonstration at inference time.

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 provides a unified taxonomy and controlled empirical evaluation of jailbreak attacks and defenses for Large Audio Language Models (LALMs), demonstrating that safety evaluation must consider…

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…

GuardNet is a lightweight, ensemble-based guardrail system using shallow neural networks that provides robust and efficient detection of Prompt Injection and Jailbreak attacks on LLMs, suitable for pr…

The paper introduces Tail-risk Intrinsic Geometric Smoothing (TIGS), a plug-and-play, inference-time defense that suppresses backdoor attacks on LLMs by structurally smoothing the attention mechanism…

The paper introduces Incremental Completion Decomposition (ICD), a novel jailbreak strategy that successfully bypasses LLM safety mechanisms by eliciting malicious content through a sequence of single…

The paper proposes GUARD-SLM, a token activation-based defense mechanism, to enhance the robustness of Small Language Models (SLMs) against various jailbreak attacks by analyzing and filtering malicio…

The paper introduces a new adaptive jailbreak attack (JB-GCG) that successfully bypasses the state-of-the-art JBShield defense, and proposes a more robust defense (RTV) based on multi-layer representa…

The paper proposes an unsupervised bi-level adversarial training framework to enhance LLM safety steering, achieving strong zero-shot defense against unseen and evolving jailbreak prompts.

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…

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 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 introduces Head-Masked Nullspace Steering (HMNS), a novel geometry-aware attack method that achieves state-of-the-art jailbreak success rates by manipulating the internal attention mechanism…

The paper introduces an adaptive probe-based steering method that significantly improves the robustness and effectiveness of LLM jailbreaking without requiring extra prompts or manual tuning.