33 citations · 162 across the 27 of their papers we have counts for
12 papers · 1 filter
Model Supply Chain Poisoning: Backdooring Pre-trained Models via Embedding Indistinguishability
Hao Wang, Shangwei Guo, Jialing He +3
Pre-trained models (PTMs) are widely adopted across various downstream tasks in the machine learning supply chain. Adopting untrustworthy PTMs introduces significant security risks…
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…
Privacy-preserving Decentralized Deep Learning with Multiparty Homomorphic Encryption
Guowen Xu, Guanlin Li, Shangwei Guo +2
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-po…
Threats to Pre-trained Language Models: Survey and Taxonomy
Shangwei Guo, Chunlong Xie, Jiwei Li +2
Pre-trained language models (PTLMs) have achieved great success and remarkable performance over a wide range of natural language processing (NLP) tasks. However, there are also gro…
Robust and Privacy-Preserving Collaborative Learning: A Comprehensive Survey
Shangwei Guo, Xu Zhang, Fei Yang +4
With the rapid demand of data and computational resources in deep learning systems, a growing number of algorithms to utilize collaborative machine learning techniques, for example…
PEEL: A Provable Removal Attack on Deep Hiding
Tao Xiang, Hangcheng Liu, Shangwei Guo +1
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-…
Fingerprinting Image-to-Image Generative Adversarial Networks
Guanlin Li, Guowen Xu, Han Qiu +5
Generative Adversarial Networks (GANs) have been widely used in various application scenarios. Since the production of a commercial GAN requires substantial computational and human…
Ownership Verification of DNN Architectures via Hardware Cache Side Channels
Xiaoxuan Lou, Shangwei Guo, Jiwei Li +1
Deep Neural Networks (DNN) are gaining higher commercial values in computer vision applications, e.g., image classification, video analytics, etc. This calls for urgent demands of…
DeepSweep: An Evaluation Framework for Mitigating DNN Backdoor Attacks using Data Augmentation
Han Qiu, Yi Zeng, Shangwei Guo +3
Public resources and services (e.g., datasets, training platforms, pre-trained models) have been widely adopted to ease the development of Deep Learning-based applications. However…
Fine-tuning Is Not Enough: A Simple yet Effective Watermark Removal Attack for DNN Models
Shangwei Guo, Tianwei Zhang, Han Qiu +3
Watermarking has become the tendency in protecting the intellectual property of DNN models. Recent works, from the adversary's perspective, attempted to subvert watermarking mechan…
Topology-aware Differential Privacy for Decentralized Image Classification
Shangwei Guo, Tianwei Zhang, Guowen Xu +3
In this paper, we design Top-DP, a novel solution to optimize the differential privacy protection of decentralized image classification systems. The key insight of our solution is…