Wei, Shaokui

10 publications

ICLR 2025 Activation Gradient Based Poisoned Sample Detection Against Backdoor Attacks Danni Yuan, Mingda Zhang, Shaokui Wei, Li Liu, Baoyuan Wu

ICCV 2025 Backdoor Mitigation by Distance-Driven Detoxification Shaokui Wei, Jiayin Liu, Hongyuan Zha

NeurIPS 2024 Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor Shaokui Wei, Hongyuan Zha, Baoyuan Wu

NeurIPS 2024 Unveiling and Mitigating Backdoor Vulnerabilities Based on Unlearning Weight Changes and Backdoor Activeness Weilin Lin, Li Liu, Shaokui Wei, Jianze Li, Hui Xiong

ICLR 2024 VDC: Versatile Data Cleanser Based on Visual-Linguistic Inconsistency by Multimodal Large Language Models Zihao Zhu, Mingda Zhang, Shaokui Wei, Bingzhe Wu, Baoyuan Wu

ICCV 2023 Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization Mingli Zhu, Shaokui Wei, Li Shen, Yanbo Fan, Baoyuan Wu

AISTATS 2023 Mean Parity Fair Regression in RKHS Shaokui Wei, Jiayin Liu, Bing Li, Hongyuan Zha

NeurIPS 2023 Neural Polarizer: A Lightweight and Effective Backdoor Defense via Purifying Poisoned Features Mingli Zhu, Shaokui Wei, Hongyuan Zha, Baoyuan Wu

NeurIPS 2023 Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples Shaokui Wei, Mingda Zhang, Hongyuan Zha, Baoyuan Wu

NeurIPS 2022 BackdoorBench: A Comprehensive Benchmark of Backdoor Learning Baoyuan Wu, Hongrui Chen, Mingda Zhang, Zihao Zhu, Shaokui Wei, Danni Yuan, Chao Shen