5 citations · 10 across the 7 of their papers we have counts for
8 papers
Boosting Generative Adversarial Transferability with Self-supervised Vision Transformer Features
Shangbo Wu, Yu-an Tan, Ruinan Ma +3
The ability of deep neural networks (DNNs) come from extracting and interpreting features from the data provided. By exploiting intermediate features in DNNs instead of relying on…
Towards Transferable Adversarial Attacks with Centralized Perturbation
Shangbo Wu, Yu-an Tan, Yajie Wang +3
Adversarial transferability enables black-box attacks on unknown victim deep neural networks (DNNs), rendering attacks viable in real-world scenarios. Current transferable attacks…
Unified High-binding Watermark for Unconditional Image Generation Models
Ruinan Ma, Yu-an Tan, Shangbo Wu +3
Deep learning techniques have implemented many unconditional image generation (UIG) models, such as GAN, Diffusion model, etc. The extremely realistic images (also known as AI-Gene…
Towards Invisible Backdoor Attacks in the Frequency Domain against Deep Neural Networks
Xinrui Liu, Yajie Wang, Yu-an Tan +2
Deep neural networks (DNNs) have made tremendous progress in the past ten years and have been applied in various critical applications. However, recent studies have shown that deep…
Stealthy Low-frequency Backdoor Attack against Deep Neural Networks
Xinrui Liu, Yu-an Tan, Yajie Wang +2
Deep neural networks (DNNs) have gain its popularity in various scenarios in recent years. However, its excellent ability of fitting complex functions also makes it vulnerable to b…
Enhancing Clean Label Backdoor Attack with Two-phase Specific Triggers
Nan Luo, Yuanzhang Li, Yajie Wang +3
Backdoor attacks threaten Deep Neural Networks (DNNs). Towards stealthiness, researchers propose clean-label backdoor attacks, which require the adversaries not to alter the labels…
l-Leaks: Membership Inference Attacks with Logits
Shuhao Li, Yajie Wang, Yuanzhang Li +1
Machine Learning (ML) has made unprecedented progress in the past several decades. However, due to the memorability of the training data, ML is susceptible to various attacks, espe…
Improving the Transferability of Adversarial Examples with Restructure Embedded Patches
Huipeng Zhou, Yu-an Tan, Yajie Wang +3
Vision transformers (ViTs) have demonstrated impressive performance in various computer vision tasks. However, the adversarial examples generated by ViTs are challenging to transfe…