Integrating machine learning detection and encrypted control for enhanced cybersecurity of nonlinear processes

被引:11
作者
Kadakia, Yash A. [1 ]
Suryavanshi, Atharva [1 ]
Alnajdi, Aisha [2 ]
Abdullah, Fahim [1 ]
Christofides, Panagiotis D. [1 ,2 ]
机构
[1] Univ Calif Los Angeles, Dept Chem & Biomol Engn, Los Angeles, CA 90095 USA
[2] Univ Calif Los Angeles, Dept Elect & Comp Engn, Los Angeles, CA 90095 USA
基金
美国国家科学基金会;
关键词
Model predictive control; Encrypted control; Machine learning; Cybersecurity; Semi-homomorphic encryption; Quantization; MODEL-PREDICTIVE CONTROL; PROCESS SYSTEMS; ARCHITECTURE; STATE;
D O I
10.1016/j.compchemeng.2023.108498
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
This study presents an encrypted two-tier control architecture integrated with a machine learning (ML) based cyberattack detector to enhance the operational safety, cyber-security, and performance of nonlinear processes. The upper tier of this architecture employs an encrypted nonlinear Lyapunov-based model predictive controller (LMPC) to enhance closed-loop performance, while the lower tier utilizes an encrypted set of linear controllers to stabilize the process. Encrypted signals from the sensors are decrypted at the upper tier for plain text control input computation, while the lower tier computes control inputs in an encrypted space, due to its exclusive use of linear operations. While this design enhances closed-loop performance, it exposes the upper tier to potential cyberattacks. To mitigate this risk, an ML-based detector is developed in the form of a feed-forward neural network, utilizing sensor-derived data for attack detection. Upon attack detection, the control system logic deactivates the performance-enhancing upper tier and relies solely on the cybersecure lower tier for system stabilization. The study also includes a comprehensive stability analysis of the two-tier control structure, establishing error bounds related to quantization and sample-and-hold controller implementations. The proposed control framework can be extended to any nonlinear process that is controlled by a combination of linear and nonlinear controllers to enhance the system cybersecurity. Guidelines such as quantization parameter selection, cyberattack detector development, and sampling time criteria are included to facilitate practical implementation. Simulation results of a nonlinear chemical process network demonstrated the robustness of the encrypted control architecture and cyberattack detector, as well as its ability to detect previously unseen attack patterns.
引用
收藏
页数:21
相关论文
共 25 条
[1]   Survey on Anomaly Detection using Data Mining Techniques [J].
Agrawal, Shikha ;
Agrawal, Jitendra .
KNOWLEDGE-BASED AND INTELLIGENT INFORMATION & ENGINEERING SYSTEMS 19TH ANNUAL CONFERENCE, KES-2015, 2015, 60 :708-713
[2]  
Bomze I.M., 2010, Nonlinear Optimization: Lectures given at the C.I.M.E. Summer School held in Cetraro, Italy, July 1-7
[3]   A cyber-secure control-detector architecture for nonlinear processes [J].
Chen, Scarlett ;
Wu, Zhe ;
Christofides, Panagiotis D. .
AICHE JOURNAL, 2020, 66 (05)
[4]   Towards Encrypted MPC for Linear Constrained Systems [J].
Darup, Moritz Schulze ;
Redder, Adrian ;
Shames, Iman ;
Farokhi, Farhad ;
Quevedo, Daniel .
IEEE CONTROL SYSTEMS LETTERS, 2018, 2 (02) :195-200
[5]  
Data C., 2013, Python paillier library
[6]   Mitigating Safety Concerns and Profit/Production Losses for Chemical Process Control Systems under Cyberattacks via Design/Control Methods [J].
Durand, Helen ;
Wegener, Matthew .
MATHEMATICS, 2020, 8 (04)
[7]   A Nonlinear Systems Framework for Cyberattack Prevention for Chemical Process Control Systems [J].
Durand, Helen .
MATHEMATICS, 2018, 6 (09)
[8]   Economic model predictive control of nonlinear process systems using Lyapunov techniques [J].
Heidarinejad, Mohsen ;
Liu, Jinfeng ;
Christofides, Panagiotis D. .
AICHE JOURNAL, 2012, 58 (03) :855-870
[9]   Communication-efficient online detection of network-wide anomalies [J].
Huang, Ling ;
Nguyen, XuanLong ;
Garofalakis, Minos ;
Hellerstein, Joseph M. ;
Jordan, Michael I. ;
Joseph, Anthony D. ;
Taft, Nina .
INFOCOM 2007, VOLS 1-5, 2007, :134-+
[10]   Encrypted Model Predictive Control of a Nonlinear Chemical Process Network [J].
Kadakia, Yash A. ;
Suryavanshi, Atharva ;
Alnajdi, Aisha ;
Abdullah, Fahim ;
Christofides, Panagiotis D. .
PROCESSES, 2023, 11 (08)