OpenReview
.net
OpenReview
.net
Login
OpenReview
.net
Login
Zihan Guan
PhD student, University of Virginia, Charlottesville
Joined
September 2022
Names
Zihan Guan
(Preferred)
,
zihan guan
Emails
****@uga.edu
(Confirmed)
,
****@virginia.edu
(Confirmed)
Personal Links
Homepage
Google Scholar
DBLP
Career & Education History
PhD student
University of Virginia, Charlottesville
(virginia.edu)
2023
–
2028
MS student
Imperial College London
(ic.ac.uk)
2020
–
2021
Advisors, Relations & Conflicts
PhD Advisor
Anil Vullikanti
Present
Expertise
LLM Safety
2025
–
Present
AI for Healthcare
2025
–
Present
Differerential Privacy
2023
–
Present
Backdoor Attacks
2021
–
2022
Adversarial Attacks
2020
–
2021
Publications
Alignment-Weighted DPO: A principled reasoning approach to improve safety alignment
Mengxuan Hu
,
Vivek Datla
,
Anoop Kumar
,
Zihan Guan
,
Sheng Li
,
Alfy Samuel
,
Daben Liu
ICLR 2026 Poster
Readers:
Everyone
Demo: PharmaData-Agent: A Specialized Agent for Pharmaceutical Data Analysis
Zihan Guan
,
Hanyin Wang
,
Zhongliang Zhou
,
Qiaohui Zhou
,
Peining Tao
,
Junshui Ma
GenAI4Health 2025 Poster
Readers:
Everyone
BalancEdit: Dynamically Balancing the Generality-Locality Trade-off in Multi-modal Model Editing
Dongliang Guo
,
Mengxuan Hu
,
Zihan Guan
,
Thomas Hartvigsen
,
Sheng Li
ICML 2025 poster
Readers:
Everyone
Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety
Zihan Guan
,
Mengxuan Hu
,
Ronghang Zhu
,
Sheng Li
,
Anil Vullikanti
ICML 2025 spotlightposter
Readers:
Everyone
Backdoor in Seconds: Unlocking Vulnerabilities in Large Pre-trained Models via Model Editing
Dongliang Guo
,
Mengxuan Hu
,
Zihan Guan
,
Junfeng Guo
,
Thomas Hartvigsen
,
Sheng Li
Submitted to ICLR 2025
Readers:
Everyone
No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users
Mengxuan Hu
,
Hongyi Wu
,
Zihan Guan
,
Ronghang Zhu
,
Dongliang Guo
,
Daiqing Qi
,
Sheng Li
Submitted to ICLR 2025
Readers:
Everyone
BalancEdit: Dynamically Balancing the Generality-Locality Trade-off in Multi-modal Model Editing
Dongliang Guo
,
Mengxuan Hu
,
Zihan Guan
,
Thomas Hartvigsen
,
Sheng Li
ICLR 2025 Conference Withdrawn Submission
Readers:
Everyone
Mind Control through Causal Inference: Predicting Clean Images from Poisoned Data
Mengxuan Hu
,
Zihan Guan
,
Yi Zeng
,
Junfeng Guo
,
Zhongliang Zhou
,
Jielu Zhang
,
Ruoxi Jia
,
Anil Kumar Vullikanti
,
Sheng Li
ICLR 2025 Poster
Readers:
Everyone
BBCaL: Black-box Backdoor Detection under the Causality Lens
Mengxuan Hu
,
Zihan Guan
,
Junfeng Guo
,
Zhongliang Zhou
,
Jielu Zhang
,
Sheng Li
Accepted by TMLR
Readers:
Everyone
Causality-Based Black-Box Backdoor Detection
Mengxuan Hu
,
Zihan Guan
,
Zhongliang Zhou
,
Jielu Zhang
,
Sheng Li
Submitted to ICLR 2024
Readers:
Everyone
View all 16 publications
Co-Authors
Alfy Samuel
Anil Vullikanti
Anoop Kumar
Daben Liu
Daiqing Qi
Dongliang Guo
Dufan Wu
Hanyin Wang
Hongyi Wu
Hui Ren
Jielu Zhang
Jin Sun
Junfeng Guo
Junshui Ma
Lichao Sun
Mengnan Du
Mengxuan Hu
Ninghao Liu
Peining Tao
Qiaohui Zhou
Quanzheng Li
Ronghang Zhu
Ruoxi Jia
Sheng Li
Thomas Hartvigsen
View all 33 co-authors