Backdoor Attacks have been a serious vulnerability against Large Language Models (LLMs). However, previous methods only reveal such risk in specific models, or present tasks transferability after attacking the pre-trained phase. So, how risky is the model transferability of a backdoor attack? In this paper, we focus on whether existing mini-LLMs may be unconsciously instructed in backdoor knowledge by poisoned teacher LLMs through knowledge distillation (KD). Specifically, we propose ATBA, an adaptive transferable backdoor attack, which can effectively distill the backdoor of teacher LLMs into small models when only executing clean-tuning. We first propose the Target Trigger Generation (TTG) module that filters out a set of indicative trigger candidates from the token list based on cosine similarity distribution. Then, we exploit a shadow model to imitate the distilling process and introduce an Adaptive Trigger Optimization (ATO) module to realize a gradient-based greedy feedback to search optimal triggers. Extensive experiments show that ATBA generates not only positive guidance for student models but also implicitly transfers backdoor knowledge. Our attack is robust and stealthy, with over 80% backdoor transferability, and hopes the attention of security.
INK: Inheritable Natural Backdoor Attack Against Model Distillation
Institute of Computer Application, China Academy of Engineering Physics(中国工程物理研究院计算机应用研究所);Faculty of Electronic and Information Engineering, Xi’an Jiaotong University(西安交通大学电子与信息工程学院);School of Cyberspace Security, Beijing University of Posts and Telecommunications(北京邮电大学网络空间安全学院)
针对可信数据集蒸馏可阻断传统投毒后门的问题,本文提出 INK,以自然图像方差为触发器,在无训练数据访问权时实现可从教师迁移到学生的干净图像、干净标签攻击,蒸馏后 ASR 仍超 98%。
Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack
State Key Laboratory of Blockchain and Data Security(区块链与数据安全国家重点实验室);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);Nanyang Technological University(南洋理工大学)
Mutual Information Guided Backdoor Mitigation for Pre-trained Encoders
State Key Laboratory for Novel Software Technology, Nanjing University(南京大学新型软件技术国家重点实验室);College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算机与数据科学学院)
Semantic-level Backdoor Attack against Text-to-Image Diffusion Models
College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China(复旦大学计算机科学与人工智能学院,上海,中国);State Key Laboratory of Integrated Services Networks, Xidian University, Xian, China(集成服务网络国家重点实验室,西安电子科技大学,西安,中国);University of Electronic Science and Technology of China, Sichuan, China(电子科技大学,四川,中国);Ajou University, Gyeonggi-do, South Korea(庆尚道,韩国,全州大学)
Leveraging Diffusion-Based Image Variations for Robust Training on Poisoned Data
Technical University of Darmstadt(达姆施塔特工业大学);Centre for Cognitive Science(认知科学中心);German Research Center for Artificial Intelligence (DFKI)(德国人工智能研究中心(DFKI));Hessian Center for AI (hessian.AI)(黑森人工智能中心(hessian.AI))
Mark Your LLM: Detecting the Misuse of Open-Source Large Language Models via Watermarking
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Tsinghua University(清华大学);The Hong Kong University of Science and Technology(香港科技大学)