Guanhong Tao

I am an Assistant Professor in Kahlert School of Computing at 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. I am broadly interested in a range of topics in security and privacy relating to machine learning, including adversarial generative AI, security/privacy of LLM agents, 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, and ICSE / FSE. I am a recipient of Maurice H. Halstead Memorial Award (2023), ECCV AROW Workshop Best Paper Award (2022), and ACM SIGPLAN Distinguished Paper Award (2019).
I obtained my Ph.D. from Purdue University under the supervision of Dr. Xiangyu Zhang. I received my bachelor’s degree from Zhejiang University.
News
Dec, 2024 | Our project is awarded an NVIDIA Academic Grant. Thank you for the support! |
---|---|
Oct, 2024 | One paper accepted to NeurIPS 2024 Workshop Red Teaming GenAI |
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 |
Selected Publications
Awards & Honors
-
ECCV 2022 AROW Workshop Best Paper Award, Oct 2022
-
ICLR Highlighted Reviewer, Apr 2022
-
CSAW 2021 Best Applied Security Paper Award TOP-10 Finalists, Nov 2021
-
ACM SIGPLAN Distinguished Paper Award, Oct 2019
Students
-
Kang Yang (co-advised with Dr. Jun Xu)
Teaching
-
CS 5956: Intro to Machine Learning, University of Utah, Spring 2025
-
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
- BANDS The 1st ICLR Workshop on Backdoor Attacks and Defenses in Machine Learning
- AISCC NDSS 2024 Workshop on AI System with Confidential Computing
- Program Committee / Reviewer
- S&P IEEE Symposium on Security and Privacy:
2021
(Shadow),2025
- CCS ACM Conference on Computer and Communications Security:
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
,2025
- ICLR International Conference on Learning Representations:
2022
(Highlighted),2023
,2024
,2025
- CVPR IEEE/CVF Conference on Computer Vision and Pattern Recognition:
2022
,2023
,2025
- ECCV European Conference on Computer Vision:
2022
- ICCV International Conference on Computer Vision:
2023
- ACL Annual Meeting of the Association for Computational Linguistics:
2023
,2025
- EMNLP Conference on Empirical Methods in Natural Language Processing:
2023
- AISTATS International Conference on Artificial Intelligence and Statistics:
2025
- AAAI Annual AAAI Conference on Artificial Intelligence:
2024
- DLSP Deep Learning Security and Privacy Workshop (co-located with S&P):
2025
- LLMapp International Workshop on LLM App Store Analysis (co-located with FSE):
2025
- SATA NeurIPS Workshop on Towards Safe & Trustworthy Agents:
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
- S&P IEEE Symposium on Security and Privacy: