I am currently a last-year Ph.D. candidate at Pennsylvania State University – College of Information Science and Technology and a visiting scholar at Stony Brook University – Computer Science Department. Before that, I received my master’s degree at Lehigh University and my bachelor’s degree at Nanjing University of Aeronautics and Astronautics.
My research focuses on AI Security and Privacy, aiming at studying adversarial AI techniques and developing responsible, robust, and resilient strategies to improve AI’s reliability. My research involves AI applications in various domains, including Graph Learning, Large Language Models, Prompt Engineering, AutoML, and Contrastive Learning.
I am currently on the 2023-2024 academic job market, looking for research positions in CS, related to Security and Privacy, Artificial Intelligence, Machine Learning, and Data Science. Please feel free to contact me if you are interested. I am also happy to give talks on my research in related seminars.
🔎 Research Interest:
- Adversarial/Responsible AI: security and privacy on AI/Machine Learning, trustworthy AI
- NLP: Large Language Models (LLMs), Pre-trained Language Models (PLMs), Prompt Engineering, Tool Learning
- Graph Learning: Graph Neural Networks (GNNs), Knowledge Graph, Knowledge Representation and Reasoning, Decision-making
- Advanced ML: AutoML, Constrastive Learning, Self-supervised Learning
🔥 News
- 2023.09: 🎉🎉 Our paper “Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks” was accepted by NeurIPS 2023..
- 2023.07: 🎉🎉 Our paper “An Embarrassingly Simple Backdoor Attack on Self-supervised Learning” was accepted by ICCV 2023.
- 2023.05: I start my Microsoft Internship as a Data Scientist@Seattle, WA.
- 2023.05: 🎉🎉 Our paper “On the Security Risks of Knowledge Graph Reasoning” was accepted by USENIX Security 2023.
📝 Publication
Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks
Zhaohan Xi, Tianyu Du, Changjiang Li, Ren Pang, Shouling Ji, Jinghui Chen, Fenglong Ma, Ting Wang
- Highlights: Pre-trained Language Models, Prompt Engineering, AI Security.
On the Security Risks of Knowledge Graph Reasoning
Zhaohan Xi, Tianyu Du, Changjiang Li, Ren Pang, Shouling Ji, Xiapu Luo, Xusheng Xiao, Fenglong Ma, Ting Wang
- Highlights: Knowledge Graph, Reasoning, AI Security, Decision-making, Cyber Intelligence, Clinical Decision Support.
Zhaohan Xi, Ren Pang, Shouling Ji, Ting Wang
- Highlights: Graph Learning, Graph Neural Networks (GNNs), Backdoor (Trojaning) Attack.
📖 Education
- 2023.08 - 2024.05 (expected), Visiting Scholar, Stony Brook University.
- 2020.01 - 2024.05 (expected), Ph.D., Pennsylvania State University.
- 2016.08 - 2018.05, Master, Lehigh University.
- 2012.09 - 2016.06, Bachelor, Nanjing University of Aeronautics and Astronautics.
💻 Internship
- 2023.05 - 2023.08, Microsoft Data Scientist Internship, Seattle, WA.
- 2022.05 - 2022.08, Uber Ph.D. Software Engineering Internship, Sunnyvale, CA.