Defending Against Model Inversion Attack by Adversarial Examples
2021 IEEE International Conference on Cyber Security and Resilience (CSR)(2021)
摘要
Model inversion (MI) attacks aim to infer and reconstruct the input data from the output of a neural network, which poses a severe threat to the privacy of input data. Inspired by adversarial examples, we propose defending against MI attacks by adding adversarial noise to the output. The critical challenge is finding a noise vector that maximizes the inversion error and introduces negligible utili...
更多查看译文
关键词
Training,Adaptation models,Data privacy,Computational modeling,Neural networks,Turning,Distortion
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要