7 papers · 1 filter
LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts
Qibing Ren, Hao Li, Dongrui Liu +7
Safety concerns in large language models (LLMs) have gained significant attention due to their exposure to potentially harmful data during pre-training. In this paper, we identify…
Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking
Junda Zhu, Lingyong Yan, Shuaiqiang Wang +2
Large Reasoning Models (LRMs) have recently demonstrated impressive performances across diverse domains. However, how the safety of Large Language Models (LLMs) benefits from enhan…
AISafetyLab: A Comprehensive Framework for AI Safety Evaluation and Improvement
Zhexin Zhang, Leqi Lei, Junxiao Yang +13
As AI models are increasingly deployed across diverse real-world scenarios, ensuring their safety remains a critical yet underexplored challenge. While substantial efforts have bee…
DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak
Hao Wang, Hao Li, Junda Zhu +4
Large Language Models (LLMs) are susceptible to generating harmful content when prompted with carefully crafted inputs, a vulnerability known as LLM jailbreaking. As LLMs become mo…
ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors
Zhexin Zhang, Yida Lu, Jingyuan Ma +8
The safety of Large Language Models (LLMs) has gained increasing attention in recent years, but there still lacks a comprehensive approach for detecting safety issues within LLMs'…
ATM: Adversarial Tuning Multi-agent System Makes a Robust Retrieval-Augmented Generator
Junda Zhu, Lingyong Yan, Haibo Shi +2
Large language models (LLMs) are proven to benefit a lot from retrieval-augmented generation (RAG) in alleviating hallucinations confronted with knowledge-intensive questions. RAG…