中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Variation Enhanced Attacks Against RRAM-Based Neuromorphic Computing System

文献类型：期刊论文

作者Lv, Hao3; Li, Bing2; Zhang, Lei3; Liu, Cheng1; Wang, Ying1
刊名IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS
出版日期2023-05-01
卷号42期号:5页码:1588-1596
关键词Security Hardware Neuromorphic engineering Computational modeling Circuit faults Resistance Immune system Adversarial attack fault injection attack neuromorphic computing system (NCS) processing in memory reliability resistive memory
ISSN号0278-0070
DOI10.1109/TCAD.2022.3207316
英文摘要The RRAM-based neuromorphic computing system (NCS) has amassed explosive interests for its superior data processing capability and energy efficiency than traditional architectures, and thus being widely used in many data-centric applications. The reliability and security issues of the NCS, therefore, become an essential problem. In this article, we systematically investigated the adversarial threats to the RRAM-based NCS and observed that the RRAM hardware feature can be leveraged to strengthen the attack effect, which has not been granted sufficient attention by previous algorithmic attack methods. Thus, we proposed two types of hardware-aware attack methods with respect to different attack scenarios and objectives. The first is an adversarial attack, VADER, which perturbs the input samples to mislead the prediction of neural networks. The second is fault injection attack, EFI, which perturbs the network parameter space such that a specified sample will be classified to a target label, while maintaining the prediction accuracy on other samples. Both attack methods leverage the RRAM properties to improve the performance compared with the conventional attack methods. Experimental results show that our hardware-aware attack methods can achieve nearly 100% attack success rate with extremely low operational cost, while maintaining the attack stealthiness.
资助项目National Natural Science Foundation of China (NSFC)[61874124] ; National Natural Science Foundation of China (NSFC)[62204164] ; National Natural Science Foundation of China (NSFC)[62222411] ; Zhejiang Lab[2021PC0AC01] ; Beijing Natural Science Foundation[4194092]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000976102300017
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
源URL[http://119.78.100.204/handle/2XEOYT63/21439]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Wang, Ying
作者单位1.Chinese Acad Sci, Inst Comp Technol, State Key Lab Comp Architecture, Beijing 100089, Peoples R China
2.Capital Normal Univ, Acad Multidisciplinary Studies, Beijing 100048, Peoples R China
3.Chinese Acad Sci, Univ Chinese Acad Sci, Inst Comp Technol, Beijing 100089, Peoples R China
推荐引用方式
GB/T 7714		 Lv, Hao,Li, Bing,Zhang, Lei,et al. Variation Enhanced Attacks Against RRAM-Based Neuromorphic Computing System[J]. IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS,2023,42(5):1588-1596.
APA Lv, Hao,Li, Bing,Zhang, Lei,Liu, Cheng,&Wang, Ying.(2023).Variation Enhanced Attacks Against RRAM-Based Neuromorphic Computing System.IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS,42(5),1588-1596.
MLA Lv, Hao,et al."Variation Enhanced Attacks Against RRAM-Based Neuromorphic Computing System".IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS 42.5(2023):1588-1596.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

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。