Name: Rozhin Yasaei
Chair: Mohammad Al Faruque
Date: May 24, 2023
Time: 3:00 PM
Location: EH 2430-Harut Barsamian
Committee: Fadi Kurdahi, Zhou Li
Title: Integrating Machine Learning for Enhanced Cross-Layer Security and Reliability in Hardware and Cyber-Physical Systems
This Ph.D. thesis presents a comprehensive investigation into addressing security and reliability challenges in hardware design and cyber-physical systems. The research leverages advanced techniques such as Graph Neural Networks (GNN) and machine learning to develop novel methodologies for anomaly detection, hardware Trojan detection, IP piracy detection, and cross-layer security analysis.
The thesis focuses on hardware security, specifically Hardware Trojan (HT) detection. A golden reference-free approach, GNN4TJ, is proposed for detecting HTs at the Register Transfer Level (RTL). By modeling hardware designs as graphs and employing GNN, GNN4TJ achieves high recall rates for identifying both known and unknown HTs.
Moving to the IoT domain, the thesis addresses security challenges in IoT systems through the development of adaptive anomaly detection methods. IoT-CAD utilizes IoT sensor data and fog computing to ensure data integrity and detect anomalous incidents. The proposed methodology incorporates sensor association algorithms, LSTM neural networks, and Gaussian estimation for real-time anomaly detection. The thesis further extends the research to multi-modal data fusion, where the integration of sensor and communication data using GNN enables improved anomaly detection, source identification, and recovery in IoT systems.
In addition, the thesis explores the security aspect of wearable devices. A machine learning-based approach is proposed to detect anomalies in wearable devices that rely on NFC protocols. By leveraging system context and sensor correlations, the methodology achieves high accuracy in detecting anomalies from multiple wearable sensors.
Furthermore, the thesis delves into IP piracy detection, introducing a novel methodology that utilizes GNN to assess circuit similarities and detect IP piracy. The proposed approach proves effective in detecting IP piracy even in the presence of obfuscation techniques, providing a robust solution for protecting intellectual properties.
Overall, this thesis showcases the application of advanced techniques such as GNN and machine learning in enhancing security and reliability in hardware design, IoT systems, and wearable devices. The proposed methodologies for anomaly detection, hardware Trojan detection, IP piracy detection, and cross-layer security analysis contribute to advancing the state-of-the-art in ensuring the integrity and security of critical systems in the digital era.
Rozhin Yasaei is currently a Ph.D. candidate at the University of California Irvine, studying computer engineering under Professor Mohammad Al Faruque. She received her M.Sc. degree in computer engineering from the University of California Irvine in 2021 and her B.Sc. in electrical engineering from Sharif University of technology in 2018. Her research interests lie in applied machine learning for embedded and cyber-physical systems security. She develops new methodologies that bring principles and techniques from machine learning, such as graph neural networks, to cross-layer system security. Rozhin conducts research that spans the areas of hardware, embedded systems, and cyber-physical systems while maintaining relevance to security and reliability.
Rozhin was selected for UC Irvine’s pedagogical fellowship in 2021 and, through one year of training, received a teaching excellence certificate and the qualification to design and implement a 3-day training program for incoming graduate students to prepare them for teaching assistance. Furthermore, she received the Rising Stars in EECS Award in 2022, the iREDEFINE Professional Development Award in 2022, UCI UROP Research Discovery Fellowship in 2022, UCI Henry Samueli Endowed Scholarship in 2018, and several scholarships from different conferences.
Rozhin is devoted to promoting diversity and inclusion and supporting her fellow collages, especially the underrepresented population in STEM, by actively volunteering for panels, workshops, and conferences with similar visions and serving the community. She has been the president of the UCI chapter of the Women in CyberSecurity (WiCyS) organization since 2021 to foster women’s participation in this field. Qualified with mentoring excellence certificate, she has been selected by several programs at UCI to mentor undergraduate and graduate students.