activity
20242026
collaborators

5 papers

cs.MA2026

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…

cs.SE2026

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…

cs.CR2026

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…

cs.CR2025

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…

cs.CR2024

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…