Yicheng Zhang Research News Publication Awards Teaching Service Misc.

Yicheng (亦成) Zhang

I am a fourth-year Ph.D. candidate at UC Riverside, where I am fortunate to be advised by Prof. Nael Abu-Ghazaleh. Prior to that, I received my M.Sc. from UC Irvine and my B.S. from Sichuan University. In 2023, I spent a wonderful summer at PNNL, working with Kevin J. Barker, Andres Marquez, and Sankha Baran Dutta on microarchitectural security in multi-GPU systems.

Email /  CV  /  Scholar  /  Github  /  LinkedIn  /  Twitter

I will join George Mason University as an Assistant Professor next Spring.

GMU ranks 32nd overall (18th in Security) on CSRankings (1st in Virginia).
About GMU and Why Join Us

Me
Research Areas & Interests

My research interests lie in computer architecture and system security, with a particular focus on the following areas:

• AR/VR Security
• Software-based side-channel attacks on AR/VR [Security’23a]
• Inferring VR keystrokes via user head motion [Security’23b]
• Shared-state attacks in multi-user AR [Security’24]
• Acoustic attacks on IMU sensors in XR headsets [arXiv’25]
• Microarchitectural / System Security
• Stealing DNN models via GPU context-switching side channels [DSN’20]
• Model extraction using remote FPGA power side channels [TIFS]
• Microarchitectural attacks on NVLink [SEED’24] [arXiv’25]
• Exploiting GPU memory via Rowhammer mitigation techniques (RFM) [Security’25]
• Attacking Linux/Android file systems via syncfs [S&P’25]
Recent News

– July 2025 [Service]: I will be serving on the Program Committee for HOST 2026. Please consider submitting your work!

– July 2025 [Service]: I will be serving on the Program Committee for two AR/VR workshops: VARSE 2025 (co-located with ASE 2025) and XR Seucrity 2025 (co-located with MobiHoc 2025). Please consider submitting your work!

– June 2025 [Activity]: I will be joining George Mason University as an Assistant Professor starting next January! I am actively recruiting Ph.D. students to join my research group.

– March 2025 [Paper]: My Ph.D. dissertation has been accepted to the HOST 2025 Ph.D. Dissertation Competition! See you in San Jose!

– March 2025 [Paper]: Our paper on attacking Linux/Android file systems via syncfs has been accepted to IEEE S&P 2025! Shout out to Cheng—he will be joining the University of Rochester as a Ph.D. student. Congrats!

Publications
  • Students advised: marked with #. Co-first authors: marked with *.
  • Publications at top-tier computer science conferences : S&P (’25), USENIX Security (’23a, ’23b, ’24). Selected papers are highlighted.

arXiv 2025 NVBleed: Covert and Side-Channel Attacks on NVIDIA Multi-GPU Interconnect
Yicheng Zhang, Ravan Nazaraliyev, Sankha Baran Dutta, Andres Marquez, Kevin J. Barker, Nael Abu-Ghazaleh
PDF / BibTex

IEEE S&P 2025 I Know What You Sync: Covert and Side Channel Attacks on File Systems via syncfs
Cheng Gu#, Yicheng Zhang, Nael Abu-Ghazaleh
The 46th IEEE Symposium on Security and Privacy, San Francisco, CA, USA, May, 2025.
Acceptance Rate: 14.8% (257/1740)
PDF / BibTex

arXiv 2025 Siren Song: Manipulating Pose Estimation in XR Headsets Using Acoustic Attacks
Zijian Huang, Yicheng Zhang, Sophie Chen, Nael Abu-Ghazaleh, Jiasi Chen
PDF / BibTex

USENIX Sec 2025 Not so Refreshing: Attacking GPUs using RFM Rowhammer Mitigation
Ravan Nazaraliyev, Yicheng Zhang, Sankha Baran Dutta, Andres Marquez, Kevin J. Barker, Nael Abu-Ghazaleh
The 34th USENIX Security Symposium, Seattle, WA, USA, August, 2025.
PDF / Code
Badges: Available, Functional

SafeAR 2024 Securing Shared State in Multi-User Augmented Reality
Jiasi Chen, Carter Slocum, Yicheng Zhang, Erfan Shayegani, Pedram Zaree, Nael Abu-Ghazaleh
2024 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct), Seattle, WA, USA, October, 2024.
PDF / BibTex

USENIX Sec 2024 That Doesn't Go There: Attacks on Shared State in Multi-User Augmented Reality Applications
Carter Slocum*, Yicheng Zhang*, Erfan Shayegani, Pedram Zaree, Nael Abu-Ghazaleh, Jiasi Chen
The 33rd USENIX Security Symposium, Philadelphia, PA, USA, August, 2024.
PDF / Slides / Video / Website / Blog (In Chinese) / BibTex

IEEE SEED 2024 Beyond the Bridge: Contention-Based Covert and Side Channel Attacks on Multi-GPU Interconnect
Yicheng Zhang, Ravan Nazaraliyev, Sankha Baran Dutta, Nael Abu-Ghazaleh, Andres Marquez, Kevin J. Barker
2024 IEEE International Symposium on Secure and Private Execution Environment Design, Orlando, FL, USA, May, 2024.
PDF / Slides / BibTex

SC Workshop 2023 Accuracy-Constrained Efficiency Optimization and GPU Profiling of CNN Inference for Detecting Drainage Crossing Locations
Yicheng Zhang, Dhroov Pandey, Di Wu, Turja Kundu, Ruopu Li, Tong Shu
SC'23 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis, Denver, CO, USA, November, 2023.
PDF / Slides / BibTex

USENIX Sec 2023 Going through the motions: AR/VR keylogging from user head motions
Carter Slocum, Yicheng Zhang, Nael Abu-Ghazaleh, Jiasi Chen
The 32nd USENIX Security Symposium, Anaheim, CA, USA, August, 2023.
PDF / Slides / BibTex / Blog (In Chinese)
*Media Coverage*: [UCR News] [Game Is Hard] [Gillett News] [Tech Xplore]

USENIX Sec 2023 It's all in your head(set): Side-channel attacks on AR/VR systems
Yicheng Zhang, Carter Slocum, Jiasi Chen, Nael Abu-Ghazaleh
The 32nd USENIX Security Symposium, Anaheim, CA, USA, August, 2023.
PDF / Slides / BibTex / Blog (In Chinese)
*Media Coverage*: [UCR News] [ZME Science] [Fagen Wasanni] [Analytics Insight]

IEEE TIFS 2021 Stealing Neural Network Structure through Remote FPGA Side-channel Analysis
Yicheng Zhang, Rozhin Yasaei, Hao Chen, Zhou Li, Mohammad Abdullah Al Faruque
IEEE Transactions on Information Forensics and Security, August, 2021.
PDF / Slides / BibTex

FPGA 2021 Poster: Stealing Neural Network Structure through Remote FPGA Side-channel Analysis
Yicheng Zhang, Rozhin Yasaei, Hao Chen, Zhou Li, Mohammad Abdullah Al Faruque
The 2021 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays, Virtual Event USA, February, 2021.
Abstract BibTex

DSN 2020 Leaky DNN: Stealing Deep-Learning Model Secret with GPU Context-Switching Side-Channel
Junyi Wei*, Yicheng Zhang*, Zhe Zhou, Zhou Li, Mohammad Abdullah Al Faruque
The 50th IEEE/IFIP International Conference on Dependable Systems and Networks (DSN), Valencia, Spain, June, 2020.
Acceptance Rate: 16.5% (48/291)
PDF / Slides / Video / Code / BibTex
Honors and Awards
International Peer Educator Training Program Certification | CRLA 2023
Conference Travel Grant | UCR GSA 2023
Student Travel Grant | 1st gem5 Boot Camp 2022
Student Travel Grant | 30th USENIX Security Symposium 2021
Student Travel Grant | 42nd IEEE Symposium on Security and Privacy 2021
Dean's Distinguished Fellowship Award | UC Riverside 2021
Teaching
teaching

I was the lead instructor for an upper-division undergraduate course at UC Riverside in Summer 2024.

Design of Operating Systems (Syllabus)
Associate Instructor for CS 153 – Summer 2024

teaching While at UC Irvine, I was a teaching assistant for the following courses:

Continuous-Time Signals and Systems
TA for EECS150 - Winter 2020

Sytem Software
TA for EECS111 - Spring 2020

Object Oriented System Programming
TA for EECS40 - Fall 2020

Next Generation Search Systems
TA for CS125 - Winter 2021

Organization of Digital Computers
TA for EECS112 - Spring 2021

Professional Service

Program Committee: EISA'23, IWSEC'23, EAI ICECI'24, VARSE'25, HOST'26

Reviewer for Conference: ICPS'20, CYBER'21-24, SecureComm'23

Reviewer for Journal: IEEE TIFS, IEEE TC, IJACT, SCN, JCS, JSA, JINS

External reviewer: DATE'19/'20, CODES+ISSS'20, NDSS'20, DSN'20, RTSS'21, MICRO'22, HPCA'22

Volunteer: SEED'24, ASPLOS'24

About me
teaching

In my free time, I love to play Dota 2 with my friends. I have played this game for over 5k hours (~2% of my lifetime) ╚(″⚈ᴗ⚈)╗
In 2023, I went to Seattle to watch Ti12 with my wife and 4-month-old son.
My favorite Dota 2 team is Azure Ray (AR), and I am also researching AR security XD 好热好热

tuan

Also, I like to capture the beautiful moments of our life stories with my lovely wife, Jinrun, our 世界で一番可爱い son, Tuan and our beautiful little lions (Slow Slow and Hanna). They are all Maine Coon!

Subscribe our bilibili channel and watch our Vlog! (๑•̀ㅂ•́)و✧

A road to be a good researcher in computer architecture & security.

Awesome webpage template forked from Jon Barron.