43 citations · 60 across the 15 of their papers we have counts for
17 papers
Class-Conditional Neural Polarizer: A Lightweight and Effective Backdoor Defense by Purifying Poisoned Features
Mingli Zhu, Shaokui Wei, Hongyuan Zha +1
Recent studies have highlighted the vulnerability of deep neural networks to backdoor attacks, where models are manipulated to rely on embedded triggers within poisoned samples, de…
Revisiting the Auxiliary Data in Backdoor Purification
Shaokui Wei, Shanchao Yang, Jiayin Liu +1
Backdoor attacks occur when an attacker subtly manipulates machine learning models during the training phase, leading to unintended behaviors when specific triggers are present. To…
Backdoor Mitigation by Distance-Driven Detoxification
Shaokui Wei, Jiayin Liu, Hongyuan Zha
Backdoor attacks undermine the integrity of machine learning models by allowing attackers to manipulate predictions using poisoned training data. Such attacks lead to targeted misc…
BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning
Baoyuan Wu, Hongrui Chen, Mingda Zhang +7
As an emerging approach to explore the vulnerability of deep neural networks (DNNs), backdoor learning has attracted increasing interest in recent years, and many seminal backdoor…
Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness
Weilin Lin, Li Liu, Shaokui Wei +2
The security threat of backdoor attacks is a central concern for deep neural networks (DNNs). Recently, without poisoned data, unlearning models with clean data and then learning a…
Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor
Shaokui Wei, Hongyuan Zha, Baoyuan Wu
Data-poisoning backdoor attacks are serious security threats to machine learning models, where an adversary can manipulate the training dataset to inject backdoors into models. In…
BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning
Baoyuan Wu, Hongrui Chen, Mingda Zhang +7
As an emerging and vital topic for studying deep neural networks' vulnerability (DNNs), backdoor learning has attracted increasing interest in recent years, and many seminal backdo…
WPDA: Frequency-based Backdoor Attack with Wavelet Packet Decomposition
Zhengyao Song, Yongqiang Li, Danni Yuan +3
This work explores an emerging security threat against deep neural networks (DNNs) based image classification, i.e., backdoor attack. In this scenario, the attacker aims to inject…
Defenses in Adversarial Machine Learning: A Survey
Baoyuan Wu, Shaokui Wei, Mingli Zhu +7
Adversarial phenomenon has been widely observed in machine learning (ML) systems, especially in those using deep neural networks, describing that ML systems may produce inconsisten…
Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks
Danni Yuan, Shaokui Wei, Mingda Zhang +2
This work studies the task of poisoned sample detection for defending against data poisoning based backdoor attacks. Its core challenge is finding a generalizable and discriminativ…
VDC: Versatile Data Cleanser based on Visual-Linguistic Inconsistency by Multimodal Large Language Models
Zihao Zhu, Mingda Zhang, Shaokui Wei +2
The role of data in building AI systems has recently been emphasized by the emerging concept of data-centric AI. Unfortunately, in the real-world, datasets may contain dirty sample…
Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples
Shaokui Wei, Mingda Zhang, Hongyuan Zha +1
Backdoor attacks are serious security threats to machine learning models where an adversary can inject poisoned samples into the training set, causing a backdoored model which pred…
Boosting Backdoor Attack with A Learnable Poisoning Sample Selection Strategy
Zihao Zhu, Mingda Zhang, Shaokui Wei +3
Data-poisoning based backdoor attacks aim to insert backdoor into models by manipulating training datasets without controlling the training process of the target model. Existing at…
Neural Polarizer: A Lightweight and Effective Backdoor Defense via Purifying Poisoned Features
Mingli Zhu, Shaokui Wei, Hongyuan Zha +1
Recent studies have demonstrated the susceptibility of deep neural networks to backdoor attacks. Given a backdoored model, its prediction of a poisoned sample with trigger will be…
Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization
Mingli Zhu, Shaokui Wei, Li Shen +2
Backdoor defense, which aims to detect or mitigate the effect of malicious triggers introduced by attackers, is becoming increasingly critical for machine learning security and int…
Mean Parity Fair Regression in RKHS
Shaokui Wei, Jiayin Liu, Bing Li +1
We study the fair regression problem under the notion of Mean Parity (MP) fairness, which requires the conditional mean of the learned function output to be constant with respect t…
BackdoorBench: A Comprehensive Benchmark of Backdoor Learning
Baoyuan Wu, Hongrui Chen, Mingda Zhang +4
Backdoor learning is an emerging and vital topic for studying deep neural networks' vulnerability (DNNs). Many pioneering backdoor attack and defense methods are being proposed, su…