6 papers
Adjustable Text-Guided Backdoor Attacks with Natural-Word Triggers on Multimodal Pretrained Models
Yiyang Zhang, Chaojian Yu, Ziming Hong +4
This paper presents Text-Guided Backdoor (TGB), an adjustable backdoor attack against multimodal pretrained models that uses natural-word triggers, namely words that can naturally…
WRF4CIR: Weight-Regularized Fine-Tuning Network for Composed Image Retrieval
Yizhuo Xu, Chaojian Yu, Yuanjie Shao +3
Composed Image Retrieval (CIR) task aims to retrieve target images based on reference images and modification texts. Current CIR methods primarily rely on fine-tuning vision-langua…
Layer-Aware Analysis of Catastrophic Overfitting: Revealing the Pseudo-Robust Shortcut Dependency
Runqi Lin, Chaojian Yu, Bo Han +2
Catastrophic overfitting (CO) presents a significant challenge in single-step adversarial training (AT), manifesting as highly distorted deep neural networks (DNNs) that are vulner…
Eliminating Catastrophic Overfitting Via Abnormal Adversarial Examples Regularization
Runqi Lin, Chaojian Yu, Tongliang Liu
Single-step adversarial training (SSAT) has demonstrated the potential to achieve both efficiency and robustness. However, SSAT suffers from catastrophic overfitting (CO), a phenom…
On the Over-Memorization During Natural, Robust and Catastrophic Overfitting
Runqi Lin, Chaojian Yu, Bo Han +1
Overfitting negatively impacts the generalization ability of deep neural networks (DNNs) in both natural and adversarial training. Existing methods struggle to consistently address…
Understanding Robust Overfitting from the Feature Generalization Perspective
Chaojian Yu, Xiaolong Shi, Jun Yu +2
Adversarial training (AT) constructs robust neural networks by incorporating adversarial perturbations into natural data. However, it is plagued by the issue of robust overfitting…