A Systematic View of Model Leakage Risks in Deep Neural Network Systems

doi:10.1109/TC.2022.3148235

	A Systematic View of Model Leakage Risks in Deep Neural Network Systems
	Hu, Xing 1; Liang, Ling 2; Chen, Xiaobing 1; Deng, Lei 3; Ji, Yu 4,5; Ding, Yufei 6; Du, Zidong 1; Guo, Qi 1; Sherwood, Tim 6; Xie, Yuan 2
	2022-12-01
发表期刊	IEEE TRANSACTIONS ON COMPUTERS
ISSN	0018-9340
卷号	71 期号:12 页码:3254-3267
摘要	As deep neural networks (DNNs) continue to find applications in ever more domains, the exact nature of the neural network architecture becomes an increasingly sensitive subject, due to either intellectual property protection or risks of adversarial attacks. While prior work has explored aspects of the risk associated with model leakage, exactly which parts of the model are most sensitive and how one infers the full architecture of the DNN when nothing is known about the structure a priori are problems that have been left unexplored. In this paper we address this gap, first by presenting a schema for reasoning about model leakage holistically, and then by proposing and quantitatively evaluating DeepSniffer, a novel learning-based model extraction framework that uses no prior knowledge of the victim model. DeepSniffer is robust to architectural and system noises introduced by the complex memory hierarchy and diverse run-time system optimizations. Taking GPU platforms as a showcase, DeepSniffer performs model extraction by learning both the architecture-level execution features of kernels and the inter-layer temporal association information introduced by the common practice of DNN design. We demonstrate that DeepSniffer works experimentally in the context of an off-the-shelf Nvidia GPU platform running a variety of DNN models and that the extracted models significantly improve attempts at crafting adversarial inputs. The DeepSniffer project has been released in https://github.com/xinghu7788/DeepSniffer.
关键词	Domain-specific architecture deep learning security model security
DOI	10.1109/TC.2022.3148235
收录类别	SCI
语种	英语
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Hardware & Architecture ; Engineering, Electrical & Electronic
WOS记录号	WOS:000886309300016
出版者	IEEE COMPUTER SOC
引用统计	被引频次：5[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/20301
专题	中国科学院计算技术研究所期刊论文
通讯作者	Hu, Xing
作者单位	1.Chinese Acad Sci, State Key Lab Comp Architecture, Inst Comp Technol, Beijing 100190, Peoples R China 2.Univ Calif Santa Barbara, Dept Elect & Comp Engn, Oakland, CA 94607 USA 3.Tsinghua Univ, Dept Precis Instrument, Ctr Brain Inspired Comp Res, Beijing 100084, Peoples R China 4.Tsinghua Univ, Beijing 100084, Peoples R China 5.Univ Calif Santa Barbara, Santa Barbara, CA 93106 USA 6.Univ Calif Santa Barbara, Dept Comp Sci, Santa Barbara, CA 93106 USA
推荐引用方式 GB/T 7714	Hu, Xing,Liang, Ling,Chen, Xiaobing,et al. A Systematic View of Model Leakage Risks in Deep Neural Network Systems[J]. IEEE TRANSACTIONS ON COMPUTERS,2022,71(12):3254-3267.
APA	Hu, Xing.,Liang, Ling.,Chen, Xiaobing.,Deng, Lei.,Ji, Yu.,...&Xie, Yuan.(2022).A Systematic View of Model Leakage Risks in Deep Neural Network Systems.IEEE TRANSACTIONS ON COMPUTERS,71(12),3254-3267.
MLA	Hu, Xing,et al."A Systematic View of Model Leakage Risks in Deep Neural Network Systems".IEEE TRANSACTIONS ON COMPUTERS 71.12(2022):3254-3267.