Recent research shows that fine-tuning on benign instruction-following data can inadvertently undo the safety alignment process and increase a model's propensity to comply with harmful queries. While instruction-following fine-tuning is important, task-specific fine-tuning - where models are trained on datasets with clear ground truth answers (e.g., multiple choice questions) - can enhance model performance on specialized downstream tasks. Understanding and mitigating safety risks in the task-specific setting remains distinct from the instruction-following context due to structural differences in the data. Our work demonstrates how malicious actors can subtly manipulate the structure of almost any task-specific dataset to foster significantly more dangerous model behaviors, while maintaining an appearance of innocuity and reasonable downstream task performance. To address this issue, we propose a novel mitigation strategy that mixes in safety data which mimics the task format and prompting style of the user data, showing this is significantly more effective and efficient than existing baselines at re-establishing safety alignment while maintaining similar task performance.
Mitigating the Risk of Health Inequity Exacerbated by Large Language Models
University of Pittsburgh(匹兹堡大学);University of Pittsburgh Medical Center(匹兹堡大学医学中心);Clinical and Translational Science Institute, University of Pittsburgh(匹兹堡大学临床与转化科学研究所)
MENTOR: A Metacognition-Driven Self-Evolution Framework for Uncovering and Mitigating Implicit Domain Risks in LLMs
School of Computer Science and Technology, East China Normal University(东华大学计算机科学与技术学院);Shanghai AI Lab, Shanghai Innovation Institute(上海人工智能实验室,上海创新研究院)
Shadow in the Cache: Unveiling and Mitigating Privacy Risks of KV-cache in LLM Inference
State Key Laboratory of Blockchain and Data Security(区块链与数据安全国家重点实验室);Zhejiang University(浙江大学);Huawei Technology(华为技术);Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security(杭州高新技术区(滨江)区块链与数据安全研究院)
Robustness Risk of Conversational Retrieval: Identifying and Mitigating Noise Sensitivity in Qwen3-Embedding Model
Beijing University of Posts and Telecommunications(北京邮电大学);SenseTime(商汤科技);Beijing Key Laboratory of Network System and Network Culture(网络系统与网络文化北京市重点实验室)
RAG-CT: Mitigating Privacy Risks on Retrieval-Augmented Generation Systems via Scanning Prompt Distribution
University of Massachusetts Lowell(马萨诸塞大学洛厄尔分校);City University of Hong Kong(香港城市大学);Virginia Tech(弗吉尼亚理工大学);University of South Florida(南佛罗里达大学);Rochester Institute of Technology(罗切斯特理工学院)
Understanding and Mitigating Cross-lingual Privacy Leakage via Language-specific and Universal Privacy Neurons
King Abdullah University of Science and Technology(国王阿卜杜勒阿齐兹科学与技术大学);Provable Responsible AI and Data Analytics (PRADA) Lab(可证明负责任的人工智能与数据分析实验室);University of Copenhagen(哥本哈根大学);University of Science and Technology of China(中国科学技术大学);State University of New York at Buffalo(纽约州立大学布法罗分校);The Hong Kong Polytechnic University(香港理工大学);Zhejiang University(浙江大学)