Scholar
Zifan Wang
Google Scholar ID: HJOP3wMAAAAJ
ScaleAI
Citations & Impact
Citations
5,720
H-index
16
i10-index
20
Publications
20
Co-authors
0
Publications
Resume
Academic Achievements
- Co-authored 'Universal and Transferable Adversarial Attacks on Aligned Language Models', introducing GCG; featured in The New York Times
- Published 'Globally-Robust Neural Networks' at ICML 2021, proposing GloRo Nets for fast global robustness certification
- Paper 'Improving Robust Generalization By Directly PAC-Bayesian Bound Minimization' selected as CVPR 2023 Highlight (top 10%)
- Contributed to the WMDP benchmark and RMU unlearning method, featured in TIME magazine
- Released multiple preprints on LLM and agent safety on arXiv