Zobrazeno 1 - 10
of 190
pro vyhledávání: '"Guo, Shangwei"'
Pre-trained models (PTMs) are widely adopted across various downstream tasks in the machine learning supply chain. Adopting untrustworthy PTMs introduces significant security risks, where adversaries can poison the model supply chain by embedding hid
Externí odkaz:
http://arxiv.org/abs/2401.15883
Adversarial training (AT) is an important and attractive topic in deep learning security, exhibiting mysteries and odd properties. Recent studies of neural network training dynamics based on Neural Tangent Kernel (NTK) make it possible to reacquaint
Externí odkaz:
http://arxiv.org/abs/2312.02236
AI-Generated Content (AIGC) is gaining great popularity, with many emerging commercial services and applications. These services leverage advanced generative models, such as latent diffusion models and large language models, to generate creative cont
Externí odkaz:
http://arxiv.org/abs/2310.07726
Autor:
Yan, Xiaobei, Lou, Xiaoxuan, Xu, Guowen, Qiu, Han, Guo, Shangwei, Chang, Chip Hong, Zhang, Tianwei
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 accelerators is the confidentiality of the deployed models: model inference execu
Externí odkaz:
http://arxiv.org/abs/2308.01193
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 this paper, we challenge the robustness of existing deep hiding schemes
Externí odkaz:
http://arxiv.org/abs/2308.01512
What can Discriminator do? Towards Box-free Ownership Verification of Generative Adversarial Network
Autor:
Huang, Ziheng, Li, Boheng, Cai, Yan, Wang, Run, Guo, Shangwei, Fang, Liming, Chen, Jing, Wang, Lina
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 illegal steal or leakage. The prior studies on remote ownership verifi
Externí odkaz:
http://arxiv.org/abs/2307.15860
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 classification. This is due to (1) the lack of reasoning ability in addressi
Externí odkaz:
http://arxiv.org/abs/2305.08377
Autor:
Li, Han, Liu, Hangcheng, Guo, Shangwei, Zhou, Mingliang, Wang, Ning, Xiang, Tao, Zhang, Tianwei
Deep hiding, concealing secret information using Deep Neural Networks (DNNs), can significantly increase the embedding rate and improve the efficiency of secret sharing. Existing works mainly force on designing DNNs with higher embedding rates or fan
Externí odkaz:
http://arxiv.org/abs/2302.11918
Decentralized deep learning plays a key role in collaborative model training due to its attractive properties, including tolerating high network latency and less prone to single-point failures. Unfortunately, such a training mode is more vulnerable t
Externí odkaz:
http://arxiv.org/abs/2207.04604
Point cloud completion task aims to predict the missing part of incomplete point clouds and generate complete point clouds with details. In this paper, we propose a novel point cloud completion network, namely CompleteDT. Specifically, features are l
Externí odkaz:
http://arxiv.org/abs/2205.14999