9 papers
Practical Framework for Privacy-Preserving and Byzantine-robust Federated Learning
Baolei Zhang, Minghong Fang, Zhuqing Liu +5
Federated Learning (FL) allows multiple clients to collaboratively train a model without sharing their private data. However, FL is vulnerable to Byzantine attacks, where adversari…
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…
BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit
Biao Yi, Zekun Fei, Jianing Geng +4
Large reasoning models (LRMs) have emerged as a significant advancement in artificial intelligence, representing a specialized class of large language models (LLMs) designed to tac…
Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models
Biao Yi, Tiansheng Huang, Sishuo Chen +4
Backdoor unalignment attacks against Large Language Models (LLMs) enable the stealthy compromise of safety alignment using a hidden trigger while evading normal safety auditing. Th…