10 papers
ColluSkill: Adversarial Cross-Skill Composition for Evading Agent Skill Scanners
Puyu Zeng, Simeng Qin, Jingzhi Li +3
Agent skills are emerging as an important attack surface in LLM-based agent systems. Through an empirical study of existing skill scanners, we find that current defenses mainly ins…
Hiding in Plain Sight: A Steganographic Approach to Stealthy LLM Jailbreaks
Jianing Geng, Biao Yi, Zekun Fei +4
Jailbreak attacks pose a serious threat to Large Language Models (LLMs) by bypassing their safety mechanisms. A truly advanced jailbreak is defined not only by its effectiveness bu…
Practical Poisoning Attacks against Retrieval-Augmented Generation
Baolei Zhang, Yuxi Chen, Zhuqing Liu +4
Large language models (LLMs) have demonstrated impressive natural language processing abilities but face challenges such as hallucination and outdated knowledge. Retrieval-Augmente…
Who Taught the Lie? Responsibility Attribution for Poisoned Knowledge in Retrieval-Augmented Generation
Baolei Zhang, Haoran Xin, Yuxi Chen +6
Retrieval-Augmented Generation (RAG) integrates external knowledge into large language models to improve response quality. However, recent work has shown that RAG systems are highl…
Gradient Surgery for Safe LLM Fine-Tuning
Biao Yi, Jiahao Li, Baolei Zhang +4
Fine-tuning-as-a-Service introduces a critical vulnerability where a few malicious examples mixed into the user's fine-tuning dataset can compromise the safety alignment of Large L…
Transform Before You Query: A Privacy-Preserving Approach for Vector Retrieval with Embedding Space Alignment
Ruiqi He, Zekun Fei, Jiaqi Li +5
Vector Database (VDB) can efficiently index and search high-dimensional vector embeddings from unstructured data, crucially enabling fast semantic similarity search essential for m…