Scholar
Zhen Xiang
Google Scholar ID: BhM3udQAAAAJ
University of Georgia
Citations & Impact
Citations
1,805
H-index
21
i10-index
29
Publications
20
Co-authors
0
Publications
Resume
Academic Achievements
- Jan 2025: One paper accepted by ICLR 2025
- Oct 2024: One paper accepted by NeuroComputing
- Sep 2024: Two papers accepted by NeurIPS 2024
- Jun 2024: One paper accepted by IROS 2024 (oral)
- May 2024: Proposal 'The LLM and Agent Safety Competition 2024' accepted to NeurIPS 2024 Competition Track
- May 2024: Paper 'ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs' accepted by ACL 2024
- Jan 2024: Paper 'BIC-based Mixture Model Defense against Data Poisoning Attacks on Classifiers: A Comprehensive Study' accepted by TKDE
- Jan 2024: Paper 'BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models' accepted by ICLR 2024
- Serving as Associate Editor for IEEE TCSVT from Jan 2024 to Dec 2025
- Sep 2023: Paper 'CBD: A Certified Backdoor Detector Based on Local Dominant Probability' accepted by NeurIPS 2023
- Jul 2023: Paper 'MMBD: Post-Training Detection of Backdoor Attacks with Arbitrary Backdoor Pattern Types Using a Maximum Margin Statistic' accepted by IEEE S&P 2024
- Jul 2023: Organizing 'The Trojan Detection Challenge 2023 (LLM Edition)'
- May 2023: Paper 'UMD: Unsupervised Model Detection for X2X Backdoor Attacks' accepted by ICML 2023
- Apr 2023: Co-authored book 'Adversarial Learning and Secure AI' accepted by Cambridge University Press (published Dec 2023)
- Dec 2022: Organized the first IEEE Trojan Removal Competition
Background
- Assistant Professor at the School of Computing, University of Georgia
- Research interests include trustworthy machine learning, large foundation models, and AI agents
- Recent research focuses on AI agents powered by large foundation models, covering:
- - Deployment of AI agents in healthcare, autonomy, education, and science
- - Safety and security of AI agents in high-stakes applications
- - Development of guardrail agents addressing safety, privacy, and fairness issues in AI applications