Ruoyu Wu | 吴若宇

Logo


About Me

I received my Ph.D. in Computer Science from Purdue University in 2024, advised by Prof.Dongyan Xu and Prof.Antonio Bianchi. My Ph.D. research applies program analysis techniques, including static source code analysis, binary analysis, symbolic execution, and fuzzing, to secure or reverse engineer software specifically related to machine learning and the Internet of Things. I received my B.Sc. degree in Computer Science from Sun Yat-sen University in 2018, awarded with two National Scholarships (top 2% in the department) in 2015 and 2017.

Experiences

Software Engineer, Google
June 2024 - Current
Worked with CoreML team, optimizing on-device machine learning infra.

Software Engineer Intern, Google
May 2023 - Aug. 2023
Worked with the XLA TPU compiler team. Designed and developed a framework generates much smaller reproducers from buggy large machine learning models (e.g., Gemini).

Research Assistant, Purdue University
Aug. 2018 - June 2024
Developed program analysis techniques (e.g., static analysis, symbolic execution, formal verification) for the software that is related to machine learning and Bluetooth.

Software Engineer Intern, FMA Technology (Acquired by Ant Group)
Apr. 2018 - July 2018
Designed and implemented an optimized PageRank algorithm on a proprietary distributed graph database.

Research Assistant, The Chinese University of Hong Kong
July 2017 - Sept. 2017; Jan. 2018 - Apr. 2018
Worked with Prof.James Cheng. Developed a distributed machine learning system.

Publications

NeuroScope: Reverse Engineering Deep Neural Network on Edge Devices using Dynamic Analysis [paper] [code]
Ruoyu Wu, Muqi Zou, Arslan Khan, Taegyu Kim, Dongyan Xu, Dave (Jing) Tian, Antonio Bianchi
Proceedings of the 34th USENIX Security Symposium (USENIX Security), 2025
(acceptance rate: TBD%)

VeriBin: Adaptive Verification of Patches at the Binary Level [paper] [code]
Hongwei Wu, Jianliang Wu, Ruoyu Wu, Ayushi Sharma, Aravind Machiry, Antonio Bianchi
The Network and Distributed System Security Symposium (NDSS), 2025
(acceptance rate: TBD%)

D-Helix: A Generic Decompiler Testing Framework Using Symbolic Differentiation [paper] [code]
Muqi Zou, Arslan Khan, Ruoyu Wu, Han Gao, Antonio Bianchi, Dave (Jing) Tian
Proceedings of the 33rd USENIX Security Symposium (USENIX Security), 2024
(acceptance rate: 417/2276=18.3%)

SoK: The Long Journey of Exploiting and Defending the Legacy of King Harald Bluetooth [paper] [code]
Jianliang Wu, Ruoyu Wu, Dongyan Xu, Dave (Jing) Tian, Antonio Bianchi
Proceedings of the 45th IEEE Symposium on Security and Privacy (S&P), 2024
(acceptance rate: 261/1463=17.8%)

Are You Spying on Me? Large-Scale Analysis on IoT Data Exposure through Companion Apps [paper] [code/dataset]
Yuhong Nan*, Xueqiang Wang*, Luyi Xing, Xiaojing Liao, Ruoyu Wu, Jianliang Wu, Yifan Zhang, XiaoFeng Wang (*co-first author)
Proceedings of the 32nd USENIX Security Symposium (USENIX Security), 2023
(acceptance rate: 422/1444=29.2%)

DnD: Decompiling Deep Neural Network Compiled Binary (40-Minute Invited Talk) [link]
Ruoyu Wu, Taegyu Kim, Dave (Jing) Tian, Antonio Bianchi, Dongyan Xu
Black Hat Europe 2022

DnD: A Cross-Architecture Deep Neural Network Decompiler [paper] [code]
Ruoyu Wu, Taegyu Kim, Dave (Jing) Tian, Antonio Bianchi, Dongyan Xu
Proceedings of the 31st USENIX Security Symposium (USENIX Security), 2022
(acceptance rate: 256/1492=17.1%)

Formal Model-Driven Discovery of Bluetooth Protocol Design Vulnerabilities [paper] [code]
Jianliang Wu, Ruoyu Wu, Dongyan Xu, Dave (Jing) Tian, Antonio Bianchi
Proceedings of the 43rd IEEE Symposium on Security and Privacy (S&P), 2022
(acceptance rate: 147/1012=14.5%)

LIGHTBLUE: Automatic Profile-Aware Debloating of Bluetooth Stacks [paper] [code]
Jianliang Wu*, Ruoyu Wu*, Daniele Antonioli, Mathias Payer, Nils Ole Tippenhauer, Dongyan Xu, Dave (Jing) Tian, Antonio Bianchi (* co-first author)
Proceedings of the 30th USENIX Security Symposium (USENIX Security), 2021
(acceptance rate: 246/1316=18.7%)

Services

Program Committee
IEEE ISSRE ‘22 RSDA; ACM SenSys ‘23 Sensors S&P; SmartSP ‘24

Artifact Evaluation Committee
USENIX Security ‘22, ‘23; EuroSys ‘23

Reviewer
IEEE TIFS ‘24; IEEE IoT-J ‘24; IEEE TWC ‘24; ACM DTRAP ‘24, ACM Middleware’24

External Reviewer
IEEE S&P ‘21; USENIX Security ‘21, ‘23; ACM CCS ‘22; ISOC NDSS ‘21, ‘22, ‘23; ACM AsiaCCS ‘21, ‘22

Personal

My hobbies include skiing, soccer, badminton, video games, and importantly, playing with cats (cute pictures and gifs!).

I love traveling and living in different places