Knowledge Commons of Institute of Automation,CAS
APRIL: Finding the Achilles' Heel on Privacy for Vision Transformers | |
Jiahao, Lu1,2; Xi Sheryl, Zhang1; Tianli, Zhao1,2; Xiangyu, He1,2; Jian Cheng1 | |
2022-03 | |
会议名称 | IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR) 2022 |
会议日期 | 2022-6 |
会议地点 | New Orleans, Louisiana, USA |
摘要 | Federated learning frameworks typically require collaborators to share their local gradient updates of a common model instead of sharing training data to preserve privacy. However, prior works on Gradient Leakage Attacks showed that private training data can be revealed from gradients. So far almost all relevant works base their attacks on fully-connected or convolutional neural networks. Given the recent overwhelmingly rising trend of adapting Transformers to solve multifarious vision tasks, it is highly important to investigate the privacy risk of vision transformers. In this paper, we analyse the gradient leakage risk of self-attention based mechanism in both theoretical and practical manners. Particularly, we propose APRIL - Attention PRIvacy Leakage, which poses a strong threat to self-attention inspired models such as ViT. Showing how vision Transformers are at the risk of privacy leakage via gradients, we urge the significance of designing privacy-safer Transformer models and defending schemes. |
关键词 | Trustworthy AI Privacy-preserving machine learning |
语种 | 英语 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48881 |
专题 | 复杂系统认知与决策实验室_高效智能计算与学习 |
通讯作者 | Jian Cheng |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Jiahao, Lu,Xi Sheryl, Zhang,Tianli, Zhao,et al. APRIL: Finding the Achilles' Heel on Privacy for Vision Transformers[C],2022. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
cvpr_camera_ready.pd(2770KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论