33 citations · 162 across the 27 of their papers we have counts for
7 papers · 1 filter
Rethinking Adversarial Training with Neural Tangent Kernel
Guanlin Li, Han Qiu, Shangwei Guo +2
Adversarial training (AT) is an important and attractive topic in deep learning security, exhibiting mysteries and odd properties. Recent studies of neural network training dynamic…
Warfare:Breaking the Watermark Protection of AI-Generated Content
Guanlin Li, Yifei Chen, Jie Zhang +5
AI-Generated Content (AIGC) is rapidly expanding, with services using advanced generative models to create realistic images and fluent text. Regulating such content is crucial to p…
Erase and Repair: An Efficient Box-Free Removal Attack on High-Capacity Deep Hiding
Hangcheng Liu, Tao Xiang, Shangwei Guo +3
Deep hiding, embedding images with others using deep neural networks, has demonstrated impressive efficacy in increasing the message capacity and robustness of secret sharing. In t…
Mercury: An Automated Remote Side-channel Attack to Nvidia Deep Learning Accelerator
Xiaobei Yan, Xiaoxuan Lou, Guowen Xu +4
DNN accelerators have been widely deployed in many scenarios to speed up the inference process and reduce the energy consumption. One big concern about the usage of the accelerator…
What can Discriminator do? Towards Box-free Ownership Verification of Generative Adversarial Network
Ziheng Huang, Boheng Li, Yan Cai +5
In recent decades, Generative Adversarial Network (GAN) and its variants have achieved unprecedented success in image synthesis. However, well-trained GANs are under the threat of…
Text Classification via Large Language Models
Xiaofei Sun, Xiaoya Li, Jiwei Li +4
Despite the remarkable success of large-scale Language Models (LLMs) such as GPT-3, their performances still significantly underperform fine-tuned models in the task of text classi…
Smaller Is Bigger: Rethinking the Embedding Rate of Deep Hiding
Han Li, Hangcheng Liu, Shangwei Guo +4
Deep hiding, concealing secret information using Deep Neural Networks (DNNs), can significantly increase the embedding rate and improve the efficiency of secret sharing. Existing w…