collaborators

8 papers

cs.CR2025

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…

cs.CL2025

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…

cs.CL2025

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…

cs.CR2025

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…

cs.CR2025

CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning

Biao Yi, Tiansheng Huang, Baolei Zhang +4

Fine-tuning-as-a-service, while commercially successful for Large Language Model (LLM) providers, exposes models to harmful fine-tuning attacks. As a widely explored defense paradi…

cs.CR2025

Traceback of Poisoning Attacks to Retrieval-Augmented Generation

Baolei Zhang, Haoran Xin, Minghong Fang +4

Large language models (LLMs) integrated with retrieval-augmented generation (RAG) systems improve accuracy by leveraging external knowledge sources. However, recent research has re…