Security in deep learning

Refereed Publications

1. Qi Li, Xingyu Li, Xiaodong Cui, Keke Tang, Peican Zhu, HEPT Attack: Heuristic Perpendicular Trial for Hard-label Attacks under Limited Query Budgets, Conference on Information and Knowledge Management (CIKM), Oct 2023.
2. Pengyue Hou, Jie Han, Xingyu Li, Improving Adversarial Robustness with Self-Paced Hard-Class Pair Reweighting, The AAAI Conference on Artificial Intelligence (AAAI), Feb 2023. Source Code
3. Peican Zhu, Jinbang Hong, Xingyu Li, Keke Tang, Zhen Wang, SGMA: A Novel Adversarial Attack Approach with Improved Transferability, Complex & Intelligent Systems, 2023.
4. Pengyue Hou, Ming Zhou, Jie Han, Petr Musilek, Xingyu Li, Adversarial Fine-tune with Dynamically Regulated Adversary, IEEE International Joint Conference on Neural Networks (IJCNN), Jul 2022.