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…

The paper introduces SlotGCG, an improved jailbreak attack method that systematically searches for the most vulnerable token insertion positions (slots) within a prompt, significantly boosting attack…

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

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.

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 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 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…

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 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 argues that reporting only the best-case attack success rate for jailbreaks is insufficient, proposing new distributional metrics (VSM and UC) to better characterize the true threat posed b…

The paper argues that the standard Attack Success Rate (ASR) metric for LLM jailbreaks is unstable and systematically inflated, proposing new frameworks to account for stochasticity in both evaluation…

NeuroArmor is a white-box runtime defense that uses prompt-specific safe variants to selectively detect and mitigate jailbreak attacks, significantly reducing attack success rates while maintaining a…

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…

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…

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

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…

SelfGrader proposes a lightweight, robust guardrail for detecting LLM jailbreaks by formulating the detection problem as a numerical grading task using anchored token-level logits, achieving strong pe…