paper-with-me

Papers

Retrieval-Augmented Defense: Adaptive and Controllable Jailbreak Prevention for Large Language Models

2025-08-22 · Guangyu Yang, Jinghong Chen, Jingbiao Mei, Weizhe Lin, Bill Byrne arxiv

Large Language Models (LLMs) remain vulnerable to jailbreak attacks, which attempt to elicit harmful responses from LLMs. The evolving nature and diversity of these attacks pose many challenges for defense systems, including (1) adaptation to counter emerging attack strategies without costly retraining, and (2) control of the trade-off between safety and utility. To address these challenges, we propose Retrieval-Augmented Defense (RAD), a novel framework for jailbreak detection that incorporates a database of known attack examples into Retrieval-Augmented Generation, which is used to infer the underlying, malicious user query and jailbreak strategy used to attack the system. RAD enables training-free updates for newly discovered jailbreak strategies and provides a mechanism to balance safety and utility. Experiments on StrongREJECT show that RAD substantially reduces the effectiveness of strong jailbreak attacks such as PAP and PAIR while maintaining low rejection rates for benign queries. We propose a novel evaluation scheme and show that RAD achieves a robust safety-utility trade-off across a range of operating points in a controllable manner.

📄 PDF Abstract BibTeX arXiv:2508.16406

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval

2025-05-21 · Taiye Chen, Zeming Wei, Ang Li, Yisen Wang

Large Language Models (LLMs) are known to be vulnerable to jailbreaking attacks, wherein adversaries exploit carefully engineered prompts to induce harmful or unethical responses. Such threats have raised critical concer…

RAGRetrievalRetrieval-augmented Generation

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models

2025-05-28 · Yongcan Yu, Yanbo Wang, Ran He, Jian Liang

While (multimodal) large language models (LLMs) have attracted widespread attention due to their exceptional capabilities, they remain vulnerable to jailbreak attacks. Various defense methods are proposed to defend again…

LeakSealer: A Semisupervised Defense for LLMs Against Prompt Injection and Leakage Attacks

2025-08-01 · Francesco Panebianco, Stefano Bonfanti, Francesco Trovò, Michele Carminati arxiv

The generalization capabilities of Large Language Models (LLMs) have led to their widespread deployment across various applications. However, this increased adoption has introduced several security threats, notably in th…

SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner

2024-06-08 · Xunguang Wang, Daoyuan Wu, Zhenlan Ji, Zongjie Li 외

Jailbreaking is an emerging adversarial attack that bypasses the safety alignment deployed in off-the-shelf large language models (LLMs) and has evolved into multiple categories: human-based, optimization-based, generati…

Adversarial AttackLLM JailbreakSafety Alignment

Provable Defense Framework for LLM Jailbreaks via Noise-Augumented Alignment

2026-02-02 · Zehua Cheng, Jianwei Yang, Wei Dai, Jiahao Sun arxiv

Large Language Models (LLMs) remain vulnerable to adaptive jailbreaks that easily bypass empirical defenses like GCG. We propose a framework for certifiable robustness that shifts safety guarantees from single-pass infer…