6 citations · 17 across the 12 of their papers we have counts for
12 papers
InkDrop: Invisible Backdoor Attacks Against Dataset Condensation
He Yang, Dongyi Lv, Song Ma +4
Dataset Condensation (DC) is a data-efficient learning paradigm that synthesizes small yet informative datasets, enabling models to match the performance of full-data training. How…
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…
Artificial Intelligence Security Competition (AISC)
Yinpeng Dong, Peng Chen, Senyou Deng +49
The security of artificial intelligence (AI) is an important research area towards safe, reliable, and trustworthy AI systems. To accelerate the research on AI security, the Artifi…
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…
Boosting Adversarial Transferability of MLP-Mixer
Haoran Lyu, Yajie Wang, Yu-an Tan +3
The security of models based on new architectures such as MLP-Mixer and ViTs needs to be studied urgently. However, most of the current researches are mainly aimed at the adversari…
Unrestricted Adversarial Attacks on ImageNet Competition
Yuefeng Chen, Xiaofeng Mao, Yuan He +34
Many works have investigated the adversarial attacks or defenses under the settings where a bounded and imperceptible perturbation can be added to the input. However in the real-wo…
Demiguise Attack: Crafting Invisible Semantic Adversarial Perturbations with Perceptual Similarity
Yajie Wang, Shangbo Wu, Wenyi Jiang +3
Deep neural networks (DNNs) have been found to be vulnerable to adversarial examples. Adversarial examples are malicious images with visually imperceptible perturbations. While the…