Alert button
Picture for Shaokui Wei

Shaokui Wei

Alert button

BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning

Jan 26, 2024
Baoyuan Wu, Hongrui Chen, Mingda Zhang, Zihao Zhu, Shaokui Wei, Danni Yuan, Mingli Zhu, Ruotong Wang, Li Liu, Chao Shen

Viaarxiv icon

Defenses in Adversarial Machine Learning: A Survey

Dec 13, 2023
Baoyuan Wu, Shaokui Wei, Mingli Zhu, Meixi Zheng, Zihao Zhu, Mingda Zhang, Hongrui Chen, Danni Yuan, Li Liu, Qingshan Liu

Figure 1 for Defenses in Adversarial Machine Learning: A Survey
Figure 2 for Defenses in Adversarial Machine Learning: A Survey
Figure 3 for Defenses in Adversarial Machine Learning: A Survey
Figure 4 for Defenses in Adversarial Machine Learning: A Survey
Viaarxiv icon

VDC: Versatile Data Cleanser for Detecting Dirty Samples via Visual-Linguistic Inconsistency

Sep 28, 2023
Zihao Zhu, Mingda Zhang, Shaokui Wei, Bingzhe Wu, Baoyuan Wu

Viaarxiv icon

Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples

Jul 20, 2023
Shaokui Wei, Mingda Zhang, Hongyuan Zha, Baoyuan Wu

Figure 1 for Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples
Figure 2 for Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples
Figure 3 for Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples
Figure 4 for Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples
Viaarxiv icon

Boosting Backdoor Attack with A Learnable Poisoning Sample Selection Strategy

Jul 14, 2023
Zihao Zhu, Mingda Zhang, Shaokui Wei, Li Shen, Yanbo Fan, Baoyuan Wu

Figure 1 for Boosting Backdoor Attack with A Learnable Poisoning Sample Selection Strategy
Figure 2 for Boosting Backdoor Attack with A Learnable Poisoning Sample Selection Strategy
Figure 3 for Boosting Backdoor Attack with A Learnable Poisoning Sample Selection Strategy
Figure 4 for Boosting Backdoor Attack with A Learnable Poisoning Sample Selection Strategy
Viaarxiv icon

Neural Polarizer: A Lightweight and Effective Backdoor Defense via Purifying Poisoned Features

Jun 29, 2023
Mingli Zhu, Shaokui Wei, Hongyuan Zha, Baoyuan Wu

Figure 1 for Neural Polarizer: A Lightweight and Effective Backdoor Defense via Purifying Poisoned Features
Figure 2 for Neural Polarizer: A Lightweight and Effective Backdoor Defense via Purifying Poisoned Features
Figure 3 for Neural Polarizer: A Lightweight and Effective Backdoor Defense via Purifying Poisoned Features
Figure 4 for Neural Polarizer: A Lightweight and Effective Backdoor Defense via Purifying Poisoned Features
Viaarxiv icon

Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization

Apr 24, 2023
Mingli Zhu, Shaokui Wei, Li Shen, Yanbo Fan, Baoyuan Wu

Figure 1 for Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization
Figure 2 for Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization
Figure 3 for Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization
Figure 4 for Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization
Viaarxiv icon

Mean Parity Fair Regression in RKHS

Feb 21, 2023
Shaokui Wei, Jiayin Liu, Bing Li, Hongyuan Zha

Figure 1 for Mean Parity Fair Regression in RKHS
Figure 2 for Mean Parity Fair Regression in RKHS
Figure 3 for Mean Parity Fair Regression in RKHS
Figure 4 for Mean Parity Fair Regression in RKHS
Viaarxiv icon

BackdoorBench: A Comprehensive Benchmark of Backdoor Learning

Jun 25, 2022
Baoyuan Wu, Hongrui Chen, Mingda Zhang, Zihao Zhu, Shaokui Wei, Danni Yuan, Chao Shen, Hongyuan Zha

Figure 1 for BackdoorBench: A Comprehensive Benchmark of Backdoor Learning
Figure 2 for BackdoorBench: A Comprehensive Benchmark of Backdoor Learning
Figure 3 for BackdoorBench: A Comprehensive Benchmark of Backdoor Learning
Figure 4 for BackdoorBench: A Comprehensive Benchmark of Backdoor Learning
Viaarxiv icon