photo

Siyuan Cheng

cheng535 AT purdue.edu

West Lafayette, IN, USA

About


I am currently a thrid year Ph.D. student in the Department of Computer Science at Purdue University, advised by Prof. Xiangyu Zhang. Prior to that, I received my B.S. degree from the Department of Computer Science and Engineering of Shanghai Jiao Tong University (SJTU) in 2020. During my undergraduate, I was affiliated with the IEEE Honor Class program.

My research expertise lies in the realm of trustworthy machine learning, with a specific focus on adversarial/backdoor attacks and defenses, across various domains, including computer vision, natural language processing, self-supervised learning, and federated learning.

My current focus is on real-world applications, e.g., large language models (LLMs) and diffusion models. I am actively engaged in exploring and addressing the intricate security and privacy concerns in these sophisticated systems.

I participated in the TrojAI competition from September 2022 and worked as a core member in the team Perspecta-PurdueRutgers. We achieved top ranking on the leaderboard in Round 12, 13 and 15.

Pre-prints( *denotes equal contribution)


  • Rapid Optimization for Jailbreaking LLMs via Subconscious Exploitation and Echopraxia
  • Guangyu Shen*, Siyuan Cheng*, Kaiyuan Zhang, Guanhong Tao, Shengwei An, Lu Yan, Zhuo Zhang, Shiqing Ma, Xiangyu Zhang
  • paper bibtex
  • Opening A Pandora's Box: Things You Should Know in the Era of Custom GPTs
  • Guanhong Tao*, Siyuan Cheng*, Zhuo Zhang, Junmin Zhu, Guangyu Shen, Xiangyu Zhang
  • paper bibtex
  • Backdoor vulnerabilities in normally trained deep learning models
  • Guanhong Tao, Zhenting Wang, Siyuan Cheng, Shiqing Ma, Shengwei An, Yingqi Liu, Guangyu Shen, Zhuo Zhang, Yunshu Mao, Xiangyu Zhang
  • paper bibtex
  • Deck: Model hardening for defending pervasive backdoors
  • Guanhong Tao, Yingqi Liu, Siyuan Cheng, Shengwei An, Zhuo Zhang, Qiuling Xu, Guangyu Shen, Xiangyu Zhang
  • paper bibtex

Publications( *denotes equal contribution)


  • ODSCAN: Backdoor Scanning for Object Detection Models
  • Siyuan Cheng*, Guangyu Shen*, Guanhong Tao, Kaiyuan Zhang, Zhuo Zhang, Shengwei An, Xiangzhe Xu, Yingqi Liu, Shiqing Ma, Xiangyu Zhang
  • Proceedings of the 45th IEEE Symposiums on Security and Privacy (S&P 2024)
  • paper bibtex code
  • Exploring the Orthogonality and Linearity of Backdoor Attacks
  • Kaiyuan Zhang*, Siyuan Cheng*, Guangyu Shen, Guanhong Tao, Shengwei An, Anuran Makur, Shiqing Ma, Xiangyu Zhang
  • Proceedings of the 45th IEEE Symposiums on Security and Privacy (S&P 2024)
  • paper bibtex
  • On Large Language Models' Resilience to Coercive Interrogation
  • Zhuo Zhang, Guangyu Shen, Guanhong Tao, Siyuan Cheng, Xiangyu Zhang
  • Proceedings of the 45th IEEE Symposiums on Security and Privacy (S&P 2024)
  • paper bibtex
  • 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)
  • paper bibtex
  • 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)
  • paper bibtex code video
  • Django: Detecting Trojans in Object Detection Models via Gaussian Focus Calibration
  • Guangyu Shen*, Siyuan Cheng*, Guanhong Tao, Kaiyuan Zhang, Yingqi Liu, Shengwei An, Shiqing Ma, Xiangyu Zhang
  • Proceedings of Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023)
  • paper bibtex
  • Hard-label Black-box Universal Adversarial Patch Attack
  • Guanhong Tao, Shengwei An, Siyuan Cheng, Guangyu Shen, Xiangyu Zhang
  • Proceedings of the 32nd USENIX Security Symposium (USENIX Security 2023)
  • paper bibtex code
  • ImU: Physical Impersonating Attack for Face Recognition System with Natural Style Changes
  • Shengwei An, Yuan Yao, Qiuling Xu, Shiqing Ma, Guanhong Tao, Siyuan Cheng, Kaiyuan Zhang, Yingqi Liu, Guangyu Shen, Ian Kelk, Xiangyu Zhang
  • Proceedings of the 44rd IEEE Symposiums on Security and Privacy (S&P 2023)
  • paper bibtex code
  • 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
  • Proceedings of the Eleventh International Conference on Learning Representations (ICLR 2023)
  • ECCV 2022 Workshop on Adversarial Robustness in the Real World (AROW 2023) Best Paper Award
  • paper bibtex code
  • 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 (CVPR 2023)
  • paper bibtex code
  • MEDIC: Remove Model Backdoors via Importance Driven Cloning
  • Qiuling Xu, Guanhong Tao, Jean Honorio, Yingqi Liu, Shengwei An, Guangyu Shen, Siyuan Cheng, Xiangyu Zhang
  • IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023)
  • paper bibtex code
  • 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)
  • paper bibtex 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)
  • paper bibtex code
  • Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification
  • Siyuan Cheng, Yingqi Liu, Shiqing Ma, Xiangyu Zhang
  • Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI 2021)
  • paper bibtex code video
  • Towards Feature Space Adversarial Attack by Style Perturbation
  • Qiuling Xu, Guanhong Tao, Siyuan Cheng, Xiangyu Zhang
  • Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI 2021)
  • paper bibtex code
  • Backdoor Scanning for Deep Neural Networks through K-Arm Optimization
  • Guangyu Shen*, Yingqi Liu*, Guanhong Tao, Shengwei An, Qiuling Xu, Siyuan Cheng, Shiqing Ma, Xiangyu Zhang
  • Proceedings of Thirty-eighth International Conference on Machine Learning (ICML 2021)
  • paper bibtex code
  • Rational Manager in Bitcoin Mining Pool: Dynamic Strategies to Gain Extra Rewards
  • Feifan Yu, Na Ruan, Siyuan Cheng
  • Proceedings of the 15th ACM Asia Conference on Computer and Communications Security (AsiaCCS 2020)
  • paper bibtex

Experience


Teaching


Services


  • Conference Reviewer
    • IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR): 2024
    • Annual Meeting of the Association for Computational Linguistics (ACL): 2024
  • Sub-reviewer
    • ACM Conference on Computer and Communications Security (CCS): 2021, 2023, 2024
    • USENIX Security Symposium: 2022
    • International Conference on Software Engineering (ICSE): 2023
    • International Conference on Automated Software Engineering (ASE): 2023