Guanhong Tao

me.png

I am an Assistant Professor in Kahlert School of Computing at the University of Utah. My research focuses on the security and safety of AI-enabled systems, aiming to empower system providers and individual users to counteract attacks and biases. I am broadly interested in a range of topics in Security and Privacy relating to machine learning, including backdoor threats, adversarial generative AI, and machine learning for security. My projects are consistently published in conferences such as IEEE S&P / USENIX Security / CCS / NDSS, NeurIPS / ICML / ICLR, CVPR / ECCV / ACL, and ICSE / FSE. I am a recipient of Maurice H. Halstead Memorial Award (for exemplary contributions to software engineering research), ECCV AROW Workshop Best Paper Award (2022), and OOPSLA Distinguished Paper Award (2019).

I obtained my Ph.D. from Purdue University under the supervision of Xiangyu Zhang. I received my bachelor’s degree from Zhejiang University.

I am looking for students interested in security and privacy at the intersection of machine learning and traditional systems.

News

Sep, 2024 One paper on detecting AI-generated text got accepted to NeurIPS 2024
Sep, 2024 Our paper on detecting backdoors in LLMs got accepted to S&P 2025
Aug, 2024 Our work on exploring inherent backdoors got accepted to ACSAC 2024
Jul, 2024 Invited to serve on the Program Committee of SaTML 2025

Selected Publications

  1. S&P
    BAIT: Large Language Model Backdoor Scanning by Inverting Attack Target
    Guangyu Shen, Siyuan Cheng, Zhuo Zhang, Guanhong Tao, Kaiyuan Zhang, Hanxi Guo, Lu Yan, Xiaolong Jin, Shengwei An, Shiqing Ma, and Xiangyu Zhang
    In Proceedings of the 46th IEEE Symposium on Security and Privacy, San Francisco, CA, USA, 2025
  2. NeurIPS
    BiScope: AI-generated Text Detection by Checking Memorization of Preceding Tokens
    Hanxi Guo, Siyuan Cheng, Xiaolong Jin, Zhuo Zhang, Kaiyuan Zhang, Guanhong Tao, Guangyu Shen, and Xiangyu Zhang
    In Proceedings of Thirty-Eighth Conference on Neural Information Processing Systems, Vancouver, Canada, 2024
  3. S&P
    Distribution Preserving Backdoor Attack in Self-supervised Learning
    Guanhong Tao*, Zhenting Wang*, Shiwei Feng, Guangyu Shen, Shiqing Ma, and Xiangyu Zhang
    In Proceedings of the 45th IEEE Symposium on Security and Privacy, San Francisco, CA, USA, 2024
  4. S&P
    On Large Language Models’ Resilience to Coercive Interrogation
    Zhuo Zhang, Guangyu Shen, Guanhong Tao, Siyuan Cheng, and Xiangyu Zhang
    In Proceedings of the 45th IEEE Symposium on Security and Privacy, San Francisco, CA, USA, 2024
  5. S&P
    Model Orthogonalization: Class Distance Hardening in Neural Networks for Better Security
    Guanhong Tao, Yingqi Liu, Guangyu Shen, Qiuling Xu, Shengwei An, Zhuo Zhang, and Xiangyu Zhang
    In Proceedings of the 43rd IEEE Symposium on Security and Privacy, San Francisco, CA, USA, 2022
  6. CVPR
    Better Trigger Inversion Optimization in Backdoor Scanning
    Guanhong Tao, Guangyu Shen, Yingqi Liu, Shengwei An, Qiuling Xu, Shiqing Ma, Pan Li, and Xiangyu Zhang
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA, 2022
  7. CCS
    ABS: Scanning Neural Networks for Back-doors by Artificial Brain Stimulation
    Yingqi Liu, Wen-Chuan Lee, Guanhong Tao, Shiqing Ma, Yousra Aafer, and Xiangyu Zhang
    In Proceedings of the 26th ACM Conference on Computer and Communications Security, London, United Kingdom, 2019

Awards & Honors

Students

Teaching

  • CS 6958 / CS 4960: Machine Learning Security, University of Utah, Fall 2024

  • Guest Lecture, CS 431: Software Engineering, Rutgers University, Spring 2023

  • Guest Lecture, CS 529: Security Analytics, Purdue University, Fall 2019, Fall 2020, Fall 2022, Fall 2023

  • Teaching Assistant, CS 240: Programming in C, Purdue University, Spring 2020

  • Teaching Assistant, CS 590: Program Analysis For Deep Learning, Purdue University, Fall 2019

Services

  • Program Chair / Organizer
  • Program Committee / Reviewer
    • S&P  IEEE Symposium on Security and Privacy: 2021 (Shadow), 2025
    • SaTML  IEEE Conference on Secure and Trustworthy Machine Learning: 2025
    • RAID  International Symposium on Research in Attacks, Intrusions and Defenses: 2024
    • FSE  ACM Symposium on the Foundations of Software Engineering: 2023 (Artifact Evaluation)
    • NeurIPS  Conference on Neural Information Processing Systems: 2021, 2022, 2023, 2024
    • ICML  International Conference on Machine Learning: 2021, 2022, 2023, 2024
    • ICLR  International Conference on Learning Representations: 2022 (Highlighted), 2023, 2024
    • CVPR  IEEE/CVF Conference on Computer Vision and Pattern Recognition: 2022, 2023
    • ECCV  European Conference on Computer Vision: 2022
    • ICCV  International Conference on Computer Vision: 2023
    • ACL  Annual Meeting of the Association for Computational Linguistics: 2023
    • EMNLP  Conference on Empirical Methods in Natural Language Processing: 2023
    • AAAI  Annual AAAI Conference on Artificial Intelligence: 2024
    • DPML  ICLR Workshop on Distributed and Private Machine Learning: 2021
    • AGI  ICLR AGI Workshop: 2024
    • TDSC  IEEE Transactions on Dependable and Secure Computing
    • T-IFS  IEEE Transactions on Information Forensics & Security
    • TOPS  ACM Transactions on Privacy and Security
    • TMLR  Transactions on Machine Learning Research