Data-Driven Modeling of Cyber-Physical Systems using Side-Channel Analysis

Sujit Rokka Chhetri is a recent graduate from the University of California, Irvine. He finished his Ph.D. in Computer Engineering from the Henry Samueli School of Engineering, where he was working as a graduate student researcher at Advanced Cyber-Physical Systems lab under the supervision of Prof. Mohammad Abdullah Al Faruque. He is currently a Staff Data Scientist at Palo Alto Networks. His research interest lies in data-driven modeling of cyber-physical systems. More specifically, his research focus is on analyzing the various source of analog emissions for potential side-channels. He is also interested in non-Euclidean data-driven modeling techniques including graph convolutional neural networks and knowledge graph embedding algorithms. Furthermore, his research also focusses on data-driven modeling techniques for building a digital twin of the cyber-physical systems. He has several publications in the top conferences and also holds one US patent. He received NDSS distinguished Poster award in 2016 as well.

1. Introduction.- 2. Data-Driven Attack Modeling using Acoustic Side-Channel.-3. Aiding Data-Driven Attack Model with a Compiler Modification.-4. Data-Driven Defense through Leakage Minimization.-5. Data-Driven Kinetic-Cyber Attack Detection.-6. Data-Driven Security Analysis using Generative Adversarial Networks.-7. Dynamic Data-Driven Digital Twin Modeling.-8. IoT-enabled Living Digital Twin Modeling.-9. Non-Euclidean Data-Driven Modeling using Graph Covolutional.-10. Dynamic Graph Graph Embedding.