Adversarial Regression for Detecting Attacks in Cyber-Physical Systems

Ghafouri, Amin; Vorobeychik, Yevgeniy; Koutsoukos, Xenofon

doi:10.24963/ijcai.2018/524

Cited by 37 publications

(31 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• most existing work is focused on supervised learning problems, while our research deals with semi-supervised learning problems, • most existing work is focused on classification tasks, while we deal with prediction (regression) tasks, • while in tasks, such as image classification, the output variable (image class) is not part of the input, in our task the input and output features are the same, and • in our case, there are multiple constraints on the internal structure of the data, due to the laws of physics and PLC logic, which are not present in other domains. A successful evasion attack framework on machine learning anomaly detection was demonstrated in [46]. The authors brought a monitored simulated Tennessee Eastman (TE) process to a dangerous pressure level by manipulating sensor measurements in a way that was classified by both a linear regression and feedforward NN as normal.…”

Section: Related Workmentioning

confidence: 99%

Efficient Cyber Attack Detection in Industrial Control Systems Using Lightweight Neural Networks and PCA

Kravchik

Shabtai

2022

IEEE Trans. Dependable and Secure Comput.

131

View full text Add to dashboard Cite

Industrial control systems (ICSs) are widely used and vital to industry and society. Their failure can have severe impact on both the economy and human life. Hence, these systems have become an attractive target for physical and cyber attacks alike. In this paper, we examine an attack detection method based on simple and lightweight neural networks, namely, 1D convolutional neural networks and autoencoders. We apply these networks to both the time and frequency domains of the data and discuss the pros and cons of each representation approach. The suggested method is evaluated on three popular public datasets, and detection rates matching or exceeding previously published detection results are achieved, while demonstrating a small footprint, short training and detection times, and generality. We also show the effectiveness of PCA, which, given proper data preprocessing and feature selection, can provide high attack detection rates in many settings. Finally, we study the proposed method's robustness against adversarial attacks that exploit inherent blind spots of neural networks to evade detection while achieving their intended physical effect. Our results show that the proposed method is robust to such evasion attacks: in order to evade detection, the attacker is forced to sacrifice the desired physical impact on the system.

show abstract

Section: Related Workmentioning

confidence: 99%

Efficient Cyber Attack Detection in Industrial Control Systems Using Lightweight Neural Networks and PCA

Kravchik

Shabtai

2022

IEEE Trans. Dependable and Secure Comput.

131

View full text Add to dashboard Cite

show abstract

“…• in our case, there are multiple constraints on the internal structure of the data, due to the laws of physics and PLC logic, that are not present in images. A successful evasion attack framework on machine learning anomaly detection was demonstrated in [44]. The authors were able to bring a monitored reactor to a dangerous pressure level by manipulating sensor measurements in a way that was classified by both a linear regression and a feed-forward neural network as normal.…”

Section: Related Workmentioning

confidence: 99%

Detecting Cyber Attacks in Industrial Control Systems Using Convolutional Neural Networks

Kravchik

Shabtai

2018

Proceedings of the 2018 Workshop on Cyber-Physical Systems Security and PrivaCy

251

167

View full text Add to dashboard Cite

Industrial control systems (ICSs) are widely used and vital to industry and society. Their failure can have severe impact on both economics and human life. Hence, these systems have become an attractive target for attacks, both physical and cyber. A number of attack detection methods have been proposed, however they are characterized by a low detection rate, a substantial false positive rate, or are system specific. In this paper, we study an attack detection method based on simple and lightweight neural networks, namely, 1D convolutions and autoencoders. We apply these networks to both the time and frequency domains of the collected data and discuss pros and cons of each approach. We evaluate the suggested method on three popular public datasets and achieve detection rates matching or exceeding previously published detection results, while featuring small footprint, short training and detection times, and generality. We also demonstrate the effectiveness of PCA, which, given proper data preprocessing and feature selection, can provide high attack detection scores in many settings. Finally, we study the proposed method's robustness against adversarial attacks, that exploit inherent blind spots of neural networks to evade detection while achieving their intended physical effect. Our results show that the proposed method is robust to such evasion attacks: in order to evade detection, the attacker is forced to sacrifice the desired physical impact on the system. This finding suggests that neural networks trained under the constraints of the laws of physics can be trusted more than networks trained under more flexible conditions.

show abstract

“…They also investigated the inertial measurement unit and wheel encoder sensors under conditions of uncertainty and non-linearity. Also, the authors in [90] used supervised regression as a means to detect anomalous sensor readings in CPS. By modeling the interaction between the CPS defender and attacker as a Stackelberg game, where the defender chooses detection thresholds in response to adversarial attacks, they proposed an algorithm for finding an approximately optimal threshold for the defender and proved that resilience can be boosted without sacrificing accuracy.…”

Section: A Attack Detection In Cpsmentioning

confidence: 99%

Resilient Machine Learning for Networked Cyber Physical Systems: A Survey for Machine Learning Security to Securing Machine Learning for CPS

Olowononi

Rawat

Liu

2021

IEEE Commun. Surv. Tutorials

146

View full text Add to dashboard Cite

Cyber Physical Systems (CPS) are characterized by their ability to integrate the physical and information or cyber worlds. Their deployment in critical infrastructure have demonstrated a potential to transform the world. However, harnessing this potential is limited by their critical nature and the far reaching effects of cyber attacks on human, infrastructure and the environment. An attraction for cyber concerns in CPS rises from the process of sending information from sensors to actuators over the wireless communication medium, thereby widening the attack surface. Traditionally, CPS security has been investigated from the perspective of preventing intruders from gaining access to the system using cryptography and other access control techniques. Most research work have therefore focused on the detection of attacks in CPS. However, in a world of increasing adversaries, it is becoming more difficult to totally prevent CPS from adversarial attacks, hence the need to focus on making CPS resilient. Resilient CPS are designed to withstand disruptions and remain functional despite the operation of adversaries. One of the dominant methodologies explored for building resilient CPS is dependent on machine learning (ML) algorithms. However, rising from recent research in adversarial ML, we posit that ML algorithms for securing CPS must themselves be resilient. This paper is therefore aimed at comprehensively surveying the interactions between resilient CPS using ML and resilient ML when applied in CPS. The paper concludes with a number of research trends and promising future research directions. Furthermore, with this paper, readers can have a thorough understanding of recent advances on ML-based security and securing ML for CPS and countermeasures, as well as research trends in this active research area.

show abstract

Adversarial Regression for Detecting Attacks in Cyber-Physical Systems

Cited by 37 publications

References 2 publications

Efficient Cyber Attack Detection in Industrial Control Systems Using Lightweight Neural Networks and PCA

Efficient Cyber Attack Detection in Industrial Control Systems Using Lightweight Neural Networks and PCA

Detecting Cyber Attacks in Industrial Control Systems Using Convolutional Neural Networks

Resilient Machine Learning for Networked Cyber Physical Systems: A Survey for Machine Learning Security to Securing Machine Learning for CPS

Contact Info

Product

Resources

About