Výsledky vyhledávání - "Liu, Hangcheng"

Report

Model Supply Chain Poisoning: Backdooring Pre-trained Models via Embedding Indistinguishability

Autor: Wang, Hao, Guo, Shangwei, He, Jialing, Liu, Hangcheng, Zhang, Tianwei, Xiang, Tao

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

Zobrazit plný text záznamu

Report

Erase and Repair: An Efficient Box-Free Removal Attack on High-Capacity Deep Hiding

Autor: Liu, Hangcheng, Xiang, Tao, Guo, Shangwei, Li, Han, Zhang, Tianwei, Liao, Xiaofeng

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

Zobrazit plný text záznamu

Report

Smaller Is Bigger: Rethinking the Embedding Rate of Deep Hiding

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

Zobrazit plný text záznamu

Akademický článek

An efficient evolutionary architecture search for variational autoencoder with alternating optimization and adaptive crossover

Autor: Shang, Ronghua, Liu, Hangcheng, Li, Wenzheng, Zhang, Weitong, Ma, Teng, Jiao, Licheng

Publikováno v: In Swarm and Evolutionary Computation April 2024 86

Zobrazit plný text záznamu

Report

PEEL: A Provable Removal Attack on Deep Hiding

Autor: Xiang, Tao, Liu, Hangcheng, Guo, Shangwei, Zhang, Tianwei

Deep hiding, embedding images into another using deep neural networks, has shown its great power in increasing the message capacity and robustness. In this paper, we conduct an in-depth study of state-of-the-art deep hiding schemes and analyze their

Externí odkaz: http://arxiv.org/abs/2106.02779

Zobrazit plný text záznamu

Report

Local Black-box Adversarial Attacks: A Query Efficient Approach

Autor: Xiang, Tao, Liu, Hangcheng, Guo, Shangwei, Zhang, Tianwei, Liao, Xiaofeng

Adversarial attacks have threatened the application of deep neural networks in security-sensitive scenarios. Most existing black-box attacks fool the target model by interacting with it many times and producing global perturbations. However, global p

Externí odkaz: http://arxiv.org/abs/2101.01032

Zobrazit plný text záznamu