5 papers
Secure Forgetting: A Framework for Privacy-Driven Unlearning in Large Language Model (LLM)-Based Agents
Dayong Ye, Tainqing Zhu, Congcong Zhu +5
Large language model (LLM)-based agents have recently gained considerable attention due to the powerful reasoning capabilities of LLMs. Existing research predominantly focuses on e…
Shapley-Guided Neural Repair Approach via Derivative-Free Optimization
Xinyu Sun, Wanwei Liu, Haoang Chi +7
DNNs are susceptible to defects like backdoors, adversarial attacks, and unfairness, undermining their reliability. Existing approaches mainly involve retraining, optimization, con…
Turning Black Box into White Box: Dataset Distillation Leaks
Huajie Chen, Tianqing Zhu, Yuchen Zhong +7
Dataset distillation compresses a large real dataset into a small synthetic one, enabling models trained on the synthetic data to achieve performance comparable to those trained on…
Isolate Trigger: Detecting and Eliminating Adaptive Backdoor Attacks
Chengrui Sun, Hua Zhang, Haoran Gao +7
Deep learning models are widely deployed in various applications but remain vulnerable to stealthy adversarial threats, particularly backdoor attacks. Backdoor models trained on po…
Watch Out! Simple Horizontal Class Backdoor Can Trivially Evade Defense
Hua Ma, Shang Wang, Yansong Gao +7
All current backdoor attacks on deep learning (DL) models fall under the category of a vertical class backdoor (VCB) -- class-dependent. In VCB attacks, any sample from a class act…