Privacy Protection in Transformer-based Neural Network | |
Lang, Jiaqi1,2; Li, Linjing1,2; Chen, Weiyun3; Zeng, Daniel1,2 | |
2019-07 | |
会议日期 | 2019年7月5日 |
会议地点 | 中国深圳 |
英文摘要 | With the great success of neural networks, it is important to improve the information security of application systems based on them. This paper investigates a scenario where an attacker eavesdrops the intermediate representation computed by the encoder layers and tries to recover the private information of the input text. We propose a new metric to evaluate the encoder's ability to protect privacy and evaluate the Transformer based encoder, which is the first privacy research conducted on Transformer-based neural networks. We also propose an adversarial |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/39075] |
专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_互联网大数据与安全信息学研究中心 |
通讯作者 | Li, Linjing |
作者单位 | 1.中国科学院大学 2.中国科学院自动化研究所 3.华中科技大学 |
推荐引用方式 GB/T 7714 | Lang, Jiaqi,Li, Linjing,Chen, Weiyun,et al. Privacy Protection in Transformer-based Neural Network[C]. 见:. 中国深圳. 2019年7月5日. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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