I am Frank Shiwei Feng, a third-year Ph.D. student from the Department of Computer Science at Purdue University. I am very fortunate to be advised by Samuel Conte Professor Xiangyu Zhang.

Previously, I obtained my B.Sc. degree in Computer Science as outstanding graduate from Nanjing University (NJU) in 2020. I am grateful to have Prof. Fengyuan Xu and Dr. Hao Wu as my initial advisors, who introduced me to the world of research. I also had the privilege to work with Dr. Lingfei Wu during my undergrad study.

My research interest lies in:

• Cyber-physical system (CPS) security & safety: both software systems and AI models in auto-driving and robotic systems.
• Deep learning security: backdoor attacks and defenses on self-supervised learning and multi-modal contrastive learning.

News

• 2024.05: I join  Apple Neural Engine Compiler Team as a Deep Learning Compiler Intern this summer! See you in South Bay Area!
• 2024.04: Our paper about adversarial attack on pixel-wise regression models is accepted by ICML 2024. Congrats to Zhiyuan!
• 2024.03: Our paper about resilient backdoor attack is accepted by CVPR 2024. Congrats to Siyuan!
• 2024.02: Our paper about adversarial attack on fusion models of auto-driving is accepted by ICLR 2024. Congrats to Zhiyuan!
• 2023.07: Our paper about backdoor attack on self-supervised learning is accepted by S&P 2024. Congrats to Guanhong and Zhenting!
• 2023.05: Receive CVPR 2023 Travel Grant Award & Registration Wavier!
• 2023.02: Our paper about backdoor detection for self-supervised learning is accepted by CVPR 2023. Thanks to all co-authors!

Publications

• BadPart: Unified Black-box Adversarial Patch Attacks against Pixel-wise Regression Tasks

  Zhiyuan Cheng, Zhaoyi Liu, Tengda Guo, Shiwei Feng, Dongfang Liu, Mingjie Tang, Xiangyu Zhang

  International Conference on Machine Learning (ICML 2024)

  Vienna, Austria, July 2024

• LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning

  Siyuan Cheng, Guanhong Tao, Yingqi Liu, Guangyu Shen, Shengwei An, Shiwei Feng, Xiangzhe Xu, Kaiyuan Zhang, Shiqing Ma, Xiangyu Zhang

  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024)

  Seattle, WA, USA, June 2024

• Fusion is Not Enough: Single-Modal Attacks to Compromise Fusion Models in Autonomous Driving

  Zhiyuan Cheng, Hongjun Choi, Shiwei Feng, James Liang, Guanhong Tao, Dongfang Liu, Michael Zuzak, Xiangyu Zhang

  International Conference on Learning Representations (ICLR 2024)

  Vienna, Austria, May 2024

• Distribution Preserving Backdoor Attack in Self-supervised Learning

  Guanhong Tao*, Zhenting Wang*, Shiwei Feng, Guangyu Shen, Shiqing Ma, Xiangyu Zhang

  Proceedings of the 45th IEEE Symposium on Security and Privacy (S&P 2024)

  San Francisco, CA, USA, May 2024

• Detecting Backdoors in Pre-trained Encoders

  Shiwei Feng, Guanhong Tao, Siyuan Cheng, Guangyu Shen, Xiangzhe Xu, Yingqi Liu, Kaiyuan Zhang, Shiqing Ma, Xiangyu Zhang

  IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023 (CVPR 2023)

  Vancouver, Canada, June 2023 [code]

• Improving Binary Code Similarity Transformer Models by Semantics-driven Instruction Deemphasis

  Xiangzhe Xu, Shiwei Feng, Yapeng Ye, Guangyu Shen, Zian Su, Siyuan Cheng, Guanhong Tao, Qingkai Shi, Zhuo Zhang, Xiangyu Zhang

  Proceedings of the 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA 2023)

  Seattle, Washington, USA, July 2023

• PEM: Representing Binary Program Semantics for Similarity Analysis via A Probabilistic Execution Model

  Xiangzhe Xu*, Zhou Xuan*, Shiwei Feng, Siyuan Cheng, Yapeng Ye, Qingkai Shi, Guanhong Tao, Le Yu, Zhuo Zhang, Xiangyu Zhang

  Proceedings of the 2023 ACM SIGSOFT International Symposium on the Foundations of Software Engineering (FSE 2023)

  San Francisco, California, USA, December 2023

• FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning

  Kaiyuan Zhang, Guanhong Tao, Qiuling Xu, Siyuan Cheng, Shengwei An, Yingqi Liu, Shiwei Feng, Guangyu Shen, Pin-Yu Chen, Shiqing Ma, Xiangyu Zhang

  International Conference on Learning Representations 2023 (ICLR 2023)

  ECCV 2022 Workshop on Adversarial Robustness in the Real World (AROW 2022), Best Paper Award

  Kigali, Rwanda, May 2023 [code]

• BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense

  Siyuan Cheng, Guanhong Tao, Yingqi Liu, Shengwei An, Xiangzhe Xu, Shiwei Feng, Guangyu Shen, Kaiyuan Zhang, Qiuling Xu, Shiqing Ma, Xiangyu Zhang

  Proceedings of the 30th Network and Distributed System Security Symposium (NDSS 2023)

  San Diego, CA, USA, February 2023 [code]

• Graph-to-Tree Neural Networks for Learning Structured Input-Output Translation with Applications to Semantic Parsing and Math Word Problem

  Shucheng Li*, Lingfei Wu*, Shiwei Feng, Fangli Xu, Fengyuan Xu and Sheng Zhong

  Conference on Empirical Methods in Natural Language Processing 2020. (EMNLP 2020 Findings)

  Hong Kong, China, November 2019 [code]

Honors and Awards

• 2023.05 CVPR 2023 DEI Travel Grant Award & Registration Wavier.
• 2022.10 Best Paper Award at ECCV 2022 AROW Workshop.
• 2022.08 1st Place (tie) in AutoDriving CTF at DEF CON 30, top 4/110 teams, hosted by Baidu Security & UC Irvine.
• 2019.10 People’s First Class Scholarship, Ministry of Education, China.
• 2018.10 Suzhou Yucai Scholarship (10 recipients among 16 STEM departments), Nanjing University.
• 2017.09 National Scholarship (Top 2%), Ministry of Education, China.

Education

• 2021.09 - Present, Ph.D. in Computer Science, Purdue University, USA
• 2016.09 - 2020.06, B.Sc. in Computer Science, Nanjing University, China

Work Experience

• 2020.07 - 2021.03, Deep Learning Compiler Engineer, Cambricon, Beijing, China

Services

• Reviewer

  ICLR 2024, ICML 2024, NeurIPS 2023-2024, IoT-J 2023-2024 (Journal)

• Artifact Evaluation Committee

  CCS 2023

• Sub-reviewer

  ICSE-CAIN 2023, ASE 2023, FSE 2024, ISSTA 2024

• Student Volunteer

  ICSE 2020

Last updated: May 31, 2024.