作者
Haonan Yan, Xiaoguang Li, Hui Li, Jiamin Li, Wenhai Sun, Fenghua Li
发表日期
2020/11/1
期刊
arXiv preprint arXiv:2011.00418
简介
Public intelligent services enabled by machine learning algorithms are vulnerable to model extraction attacks that can steal confidential information of the learning models through public queries. Though there are some protection options such as differential privacy (DP) and monitoring, which are considered promising techniques to mitigate this attack, we still find that the vulnerability persists. In this paper, we propose an adaptive query-flooding parameter duplication (QPD) attack. The adversary can infer the model information with black-box access and no prior knowledge of any model parameters or training data via QPD. We also develop a defense strategy using DP called monitoring-based DP (MDP) against this new attack. In MDP, we first propose a novel real-time model extraction status assessment scheme called Monitor to evaluate the situation of the model. Then, we design a method to guide the differential privacy budget allocation called APBA adaptively. Finally, all DP-based defenses with MDP could dynamically adjust the amount of noise added in the model response according to the result from Monitor and effectively defends the QPD attack. Furthermore, we thoroughly evaluate and compare the QPD attack and MDP defense performance on real-world models with DP and monitoring protection.
学术搜索中的文章
H Yan, X Li, H Li, J Li, W Sun, F Li - arXiv preprint arXiv:2011.00418, 2020