Privacy-Preserving Collaborative Deep Learning with Unreliable Participants

no code implementations • 25 Dec 2018 • Lingchen Zhao, Qian Wang, Qin Zou, Yan Zhang, Yanjiao Chen

With powerful parallel computing GPUs and massive user data, neural-network-based deep learning can well exert its strong power in problem modeling and solving, and has archived great success in many applications such as image classification, speech recognition and machine translation etc.

Image Classification Machine Translation +3

Shielding Collaborative Learning: Mitigating Poisoning Attacks through Client-Side Detection

no code implementations • 29 Oct 2019 • Lingchen Zhao, Shengshan Hu, Qian Wang, Jianlin Jiang, Chao Shen, Xiangyang Luo, Pengfei Hu

Collaborative learning allows multiple clients to train a joint model without sharing their data with each other.

Universal Defensive Underpainting Patch: Making Your Text Invisible to Optical Character Recognition

1 code implementation • 4 Aug 2023 • Jiacheng Deng, Li Dong, Jiahao Chen, Diqun Yan, Rangding Wang, Dengpan Ye, Lingchen Zhao, Jinyu Tian

In this work, we propose a novel and effective defense mechanism termed the Universal Defensive Underpainting Patch (UDUP) that modifies the underpainting of text images instead of the characters.

Optical Character Recognition Optical Character Recognition (OCR)

Revisiting Adversarial Training under Long-Tailed Distributions

1 code implementation • 15 Mar 2024 • Xinli Yue, Ningping Mou, Qian Wang, Lingchen Zhao

Extensive experiments further corroborate that data augmentation alone can significantly improve robustness.

Data Augmentation