Group Lunch - Fall 2022 (From left to right: Ulices, Haitham, Kohei, Momina, James, Wael, Xiaowu, Valen, Goli, Yasser)
Welcome to the Resilient Cyber-Physical Systems Lab!
The Resilient Cyber-Physical Systems lab is part of the Department of Electrical Engineering and Computer Science at the University of California, Irvine. We are physically located in the Engineering Hall Building.
Our research is in the broad area of embedded and cyber-physical systems with applications in robotics, IoT, and pervasive sensing and control. We design algorithms and build systems to enable CPS to be resilient, secure, and privacy-preserving. Our research is at the intersection of theory and systems. It draws on tools from embedded systems, formal methods, control theory, and machine learning and is motivated by real-world applications. You can read more about our research here and see videos of our research on our YouTube channel.
Are you interested in joining? We are always looking for bright and motivated talents. Please read below for more information on how to join our lab.
Recent News
Recent Publications:
- Haitham Khedr and Yasser Shoukry, “DeepBern-Nets: Taming the Complexity of Certifying Neural Networks using Bernstein Polynomial Activations and Precise Bound Propagation,” arXiv 2023.
- Ulices Santa Cruz and Yasser Shoukry, “Certified Vision-based State Estimation for Autonomous Landing Systems using Reachability Analysis,” 62nd IEEE Conference on Decision and Control (IEEE CDC), December 2023
- Momina Sajid, Yanning Shen, and Yasser Shoukry, “Model Extraction Attacks Against Reinforcement Learning Based Controllers,” arXiv 2023.
- Wael Fatnassi, Haitham Khedr, Valen Yamamoto, and Yasser Shoukry, “BERN-NN: Tight Bound Propagation For Neural Networks Using Bernstein Polynomial Interval Arithmetic,” HSCC, 2023.
- Mohanad Odema, James Ferlez, Goli Vaisi, Yasser Shoukry, Mohammad Abdullah Al Faruque, “EnergyShield: Provably-Safe Offloading of Neural Network Controllers for Energy Efficiency,” ICCPS 2023.
- Haitham Khedr and Yasser Shoukry, “CertiFair: A Framework for Certified Global Fairness of Neural Networks,” AAAI 2023.
- James Ferlez and Yasser Shoukry, “Polynomial-Time Reachability for LTI Systems with Two-Level Lattice Neural Network Controllers,” IEEE L-CSS, 2023.
- Xiaowu Sun and Yasser Shoukry, “Neurosymbolic Motion and Task Planning for Linear Temporal Logic Tasks,” arXiv 2022.
- Xiaowu Sun and Yasser Shoukry, “NNSynth: Neural Network Guided Abstraction-Based Controller Synthesis for Stochastic Systems,” CDC 2022.
- Ulices Santa Cruz, James Ferlez, and Yasser Shoukry, “Safe-by-Repair: A Convex Optimization Approach for Repairing Unsafe Two-Level Lattice Neural Network Controllers,” CDC 2022.
- Wael Fatnassi and Yasser Shoukry, “PolyARBerNN: A Neural Network Guided Solver and Optimizer for Bounded Polynomial Inequalities,” arXiv 2022.
- Ulices Santa Cruz and Yasser Shoukry, “NNLander-VeriF: A Neural Network Formal Verification Framework for Vision-Based Autonomous Aircraft Landing,” NFM 2022.
- James Ferlez, Haitham Khedr, and Yasser Shoukry, “Fast BATLLNN: Fast Box Analysis of Two-Level Lattice Neural Networks,“ HSCC 2022.
- James Ferlez and Yasser Shoukry, “Assured Neural Network Architectures for Control and Identification of Nonlinear Systems,” arXiv 2021.
- James Ferlez and Yasser Shoukry, “Bounding the Complexity of Formally Verifying Neural Networks: A Geometric Approach,” CDC 2021.
- Xiaowu Sun, Wael Fatnassi, Ulices Santa Cruz, and Yasser Shoukry, “Provably Safe Model-Based Meta Reinforcement Learning: An Abstraction-Based Approach,” CDC 2021
- Haitham Khedr, James Ferlez, and Yasser Shoukry, “PEREGRiNN: Penalized-Relaxation Greedy Neural Network Verifier,” CAV 2021.
- Wael Fatnassi and Yasser Shoukry, “PolyAR: A Highly Parallelizable Solver For Polynomial Inequality Constraints Using Convex Abstraction Refinement,“ ADHS 2021.
Funded Projects:
Role: Lead PI, Collaborators: Prof. Cody Fleming (Iowa State Univ), Prof. Min Kyung Lee (UT Austin), and Prof. Chandra Bhat (UT Austin)
CPS: Medium: ASTrA: Automated Synthesis for Trustworthy Autonomous Utility Services
Role: UCI PI, Collaborators: Prof. Pierluigi Nuzzo (USC) and Prof. Nuno Martins (UMD)
Role: Co-PI, Collaborators: Prof. Sanjit A. Seshia (UC Berkeley, PI) and Prof. Cathra Halabi (UCSF)
Completed Projects:
S&CC: Collaborative Research: SOCIUS: Socially Responsible Smart Cities
Role: Lead PI, Collaborators: Min Kyung Lee at CMU
Security and Networking Co-Design for Industrial IoT
Role: PI, Collaborators: Prof. Nuno C. Martins at UMD
Cross-Domain and Cross-Layer Safety and Security for Internet of Connected Autonomous Vehicles
Role: Co-PI, Collaborators: Prof. Mohammad Al-Faruque (PI), Prof. Fadi Kurdahi (Co-PI), Prof. Salma Elmalaki (Co-PI), Prof. Zhou Li (Co-PI), and Prof. Wenlong Jin (Co-PI)
CPS: Medium: Resilient-by-Cognition Cyber-Physical Systems
Role: PI, Collaborators: Prof. P. S. Krishnaprasad at UMD
Semantic Adversarial Analysis for Secure Critical Infrastructure
Role: Co-PI, Collaborators: Prof. Sanjit A. Seshia (UC Berkeley, PI)
Software/Hardware Support:
We are very grateful for the generous support given by the following companies:
