I am currently a Ph.D. candidate in the Department of Electrical and Computer Engineering at Princeton University, advised by Prof. Ruby B. Lee. I earned my Bachelor of Engineering degree from the Department of Microelectronics at Tsinghua University in 2016.

My primary research focus lies at the intersection of computer architecture, security, and machine learning, with the goal of developing efficient methods for attack detection and mitigation. I built versatile hardware modules that support machine learning and statistical algorithms for anomaly detection. I designed hardware features for enhancing processor security, particularly through the design of secure caches aimed at thwarting side-channel attacks and speculative execution attacks.

Publications

Conference Papers

• Zecheng He, Guangyuan Hu and Ruby B. Lee. “CloudShield: Real-time Anomaly Detection in the Cloud”. In 13th ACM Conference on Data and Application Security and Privacy (CODASPY), 2023.
• Guangyuan Hu, Zecheng He, and Ruby B. Lee. “SoK: Hardware Defenses Against Speculative Execution Attacks”. In IEEE International Symposium on Secure and Private Execution Environment Design (SEED), 2021.
• Guangyuan Hu, Zecheng He, and Ruby B. Lee. “Smartphone Impostor Detection with Behavioral Data Privacy and Minimalist Hardware Support”. In First International Research Symposium on Tiny Machine Learning (tinyML), 2021. (Best Paper Award)
• Zecheng He, Guangyuan Hu, and Ruby B. Lee. “New Models for Understanding and Reasoning about Speculative Execution Attacks”. In IEEE International Symposium on High Performance Computer Architecture (HPCA), 2021.
• Guangyuan Hu, Tianwei Zhang, Ruby B. Lee. “Position Paper: Consider Hardware-enhanced Defenses for Rootkit Attacks”. In Workshop on Hardware and Architectural Support for Security and Privacy (HASP), 2020.
• Zecheng He, Aswin Raghavan, Guangyuan Hu, Sek Chai, and Ruby B. Lee. “Power-grid Controller Anomaly Detection with Enhanced Temporal Deep Learning”. In 18th IEEE International Conference On Trust, Security And Privacy In Computing And Communications/13th IEEE International Conference On Big Data Science And Engineering (TrustCom/BigDataSE), 2019.

Preprints

• Guangyuan Hu and Ruby B. Lee. “Protecting Cache States Against Both Speculative Execution Attacks and Side-channel Attacks”. Arxiv preprint: 2302.00732, 2023.

Patent

• Ruby B. Lee and Guangyuan Hu. “Devices and Methods for Smartphone Impostor Detection Using Behavioral and Environmental Data”. U.S. Patent, 2022.

Education

• (2018 – Present) Ph. D. Candidate

  Department of Electrical and Computer Engineering, Princeton University, USA

• (2016 – 2018) Master of Arts

  Department of Electrical and Computer Engineering, Princeton University, USA

• (2012 – 2016) Bachelor of Engineering with Distinction

  Department of Microelectronics, Tsinghua University, China

Awards

• (2021) Best Paper Award, TinyML Research Symposium
• (2018) First-place Recipient of Scholarship for Siemens FutureMakers Challenge, Princeton University
• (2013,2014,2015) Scholarship for Academic Excellence, Tsinghua University

Presentations and Posters

• (2021) “Tiny AI Module for Detecting Smartphone Theft and Anomalous Behavior”. Celebrate Princeton Innovation.
• (2021) “New Models for Understanding and Reasoning about Speculative Execution Attacks”. Virtual UIUC Hardware Security Seminar.
• (2021) “SID: A Tiny Self-contained Hardware Module for Smartphone Impostor Detection”. New England Hardware Security Day.
• (2020) “Scope of Hardware Defenses Against Speculative Execution Attacks”. SRC TECHCON Conference.

Teaching and Mentoring

• (Spring 2022) Undergraduate Thesis Mentoring, Princeton University
• (Spring 2021) Undergraduate Thesis Mentoring, Princeton University
• (Fall 2020) Teaching Assistant, Architectures for Secure Computers and Smartphones, Princeton University
• (Spring 2019) Teaching Assistant, Information Signals, Princeton University