Poisoning Attacks on Cyber Attack Detectors for Industrial Control Systems

被引:20
|
作者
Kravchik, Moshe [1 ]
Biggio, Battista [2 ]
Shabtai, Asaf [1 ]
机构
[1] Ben Gurion Univ Negev, Beer Sheva, Israel
[2] Univ Cagliari, Cagliari, Italy
来源
36TH ANNUAL ACM SYMPOSIUM ON APPLIED COMPUTING, SAC 2021 | 2021年
关键词
Anomaly detection; industrial control systems; autoencoders; adversarial machine learning; poisoning attacks; adversarial robustness;
D O I
10.1145/3412841.3441892
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Recently, neural network (NN)-based methods, including autoencoders, have been proposed for the detection of cyber attacks targeting industrial control systems (ICSs). Such detectors are often retrained, using data collected during system operation, to cope with the natural evolution (i.e., concept drift) of the monitored signals. However, by exploiting this mechanism, an attacker can fake the signals provided by corrupted sensors at training time and poison the learning process of the detector such that cyber attacks go undetected at test time. With this research, we are the first to demonstrate such poisoning attacks on ICS cyber attack online NN detectors. We propose two distinct attack algorithms, namely, interpolation- and back-gradient based poisoning, and demonstrate their effectiveness on both synthetic and real-world ICS data. We also discuss and analyze some potential mitigation strategies.
引用
收藏
页码:116 / 125
页数:10
相关论文
empty
未找到相关数据