.png){kind=icon}
返回
Is Homomorphic Encryption-Based Deep Learning Secure Enough?
.png){kind=icon}
OA
AI
DOI：10.3390/s21237806.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
As the amount of data collected and analyzed by machine learning technology increases, data that can identify individuals is also being collected in large quantities. In particular, as deep learning technology-which requires a large amount of analysis data-is activated in various service fields, the possibility of exposing sensitive information of users increases, and the user privacy problem is growing more than ever. As a solution to this user's data privacy problem, homomorphic encryption technology, which is an encryption technology that supports arithmetic operations using encrypted data, has been applied to various field including finance and health care in recent years. If so, is it possible to use the deep learning service while preserving the data privacy of users by using the data to which homomorphic encryption is applied? In this paper, we propose three attack methods to infringe user's data privacy by exploiting possible security vulnerabilities in the process of using homomorphic encryption-based deep learning services for the first time. To specify and verify the feasibility of exploiting possible security vulnerabilities, we propose three attacks: (1) an adversarial attack exploiting communication link between client and trusted party; (2) a reconstruction attack using the paired input and output data; and (3) a membership inference attack by malicious insider. In addition, we describe real-world exploit scenarios for financial and medical services. From the experimental evaluation results, we show that the adversarial example and reconstruction attacks are a practical threat to homomorphic encryption-based deep learning models. The adversarial attack decreased average classification accuracy from 0.927 to 0.043, and the reconstruction attack showed average reclassification accuracy of 0.888, respectively.
Keyword:
deep learning
privacy-preserving
homomorphic encryption
adversarial examples
reconstruction attack
membership inference attack
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.5
论文数:
7.2W
被引数:
20.9W
机构
引用论文
分享收藏Current controlled voltage source inverter using Hysteresis controller and PI controller采用滞环控制器和PI控制器的电流控制电压源逆变器
PREAI
分享收藏Parkinson's disease: Nigral receptor changes support peptidergic role in nigrostriatal modulation
PREAI
分享收藏Welding characteristics of aluminum, copper, nickel and aluminum alloy with alumina coating using ultrasonic complex vibration welding equipments铝、铜、镍及铝合金氧化铝涂层超声复合振动焊接特性研究
PREAI
分享收藏Gradient-based learning applied to document recognition基于梯度的学习在文档识别中的应用.png)
PROCEEDINGS OF THE IEEE
PROCEEDINGS OF THE IEEEIF25.9
PREAI
分享收藏The effect of high intensity interval training on flexibility and anaerobic power<p>Yüksek yoğunluklu interval antrenmanın esneklik ve anaerobik kapasite üzerine etkisi高强度间歇训练对柔韧性和无氧功率的影响 y ü ksekyo ğ unluklu间隔时间和厌氧菌kapasite ü zerine etkisi
OAAI
OAAI分享收藏
查看更多内容