Personal profile
Research interests
- Large language models
- AI security
- Clinical AI
- NLP
- Graph learning
Research interests
Xi earned his PhD at Pennsylvania State University – College of Information Sciences and Technology. He was also a visiting scholar at Stony Brook University's Computer Science Department. Prior to that, he received his master’s degree from Lehigh University.
Xi's research focuses on AI security/privacy and clinical AI in the context of large language models (LLMs), aiming to develop responsible, robust and resilient strategies to improve AI’s expertise and reliability.
Beyond LLMs, his research also involves advanced AI techniques, including graph learning, knowledge graph reasoning, prompt engineering and AutoML.
Related documents
Education/Academic qualification
PhD, Pennsylvania State University
Master, Lehigh University
Researcher Selected Keywords
- Large language models
- AI security
- Clinical AI
- NLP
- Graph learning
Fingerprint
- 1 Similar Profiles
Collaborations and top research areas from the last five years
-
On the Difficulty of Defending Contrastive Learning against Backdoor Attacks
Li, C., Pang, R., Cao, B., Xi, Z., Chen, J., Ji, S. & Wang, T., 2024, Proceedings of the 33rd USENIX Security Symposium. USENIX Association, p. 2901-2918 18 p. (Proceedings of the 33rd USENIX Security Symposium).Binghamton University, Stony Brook University
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review
8 Scopus citations -
PromptFix: Few-shot Backdoor Removal via Adversarial Prompt Tuning
Zhang, T., Xi, Z., Wang, T., Mitra, P. & Chen, J., 2024, Long Papers. Duh, K., Gomez, H. & Bethard, S. (eds.). Association for Computational Linguistics (ACL), p. 3212-3225 14 p. (Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2024; vol. 1).Binghamton University, Stony Brook University
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review
Open Access1 Scopus citations -
An Embarrassingly Simple Backdoor Attack on Self-supervised Learning
Li, C., Pang, R., Xi, Z., Du, T., Ji, S., Yao, Y. & Wang, T., 2023, Proceedings - 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023. Institute of Electrical and Electronics Engineers Inc., p. 4344-4355 12 p. (Proceedings of the IEEE International Conference on Computer Vision).Binghamton University, Stony Brook University
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review
Open Access58 Scopus citations -
Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks
Xi, Z., Du, T., Li, C., Pang, R., Ji, S., Chen, J., Ma, F. & Wang, T., 2023, Advances in Neural Information Processing Systems 36 - 37th Conference on Neural Information Processing Systems, NeurIPS 2023. Oh, A., Neumann, T., Globerson, A., Saenko, K., Hardt, M. & Levine, S. (eds.). Neural information processing systems foundation, (Advances in Neural Information Processing Systems; vol. 36).Binghamton University, Stony Brook University
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review
29 Scopus citations -
On the Security Risks of Knowledge Graph Reasoning
Xi, Z., Du, T., Li, C., Pang, R., Ji, S., Luo, X., Xiao, X., Ma, F. & Wang, T., 2023, 32nd USENIX Security Symposium, USENIX Security 2023. USENIX Association, p. 3259-3276 18 p. (32nd USENIX Security Symposium, USENIX Security 2023; vol. 5).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review
6 Scopus citations