Hai Phan

Associate Professor, New Jersey Institute of Technology

Joined

July 2019

Names

Hai Phan

Emails

****@njit.edu (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

Associate Professor

New Jersey Institute of Technology (njit.edu)

2023 – Present

Assistant Professor

New Jersey Institute of Technology (njit.edu)

2016 – 2023

Postdoc

University of Oregon (uoregon.edu)

2013 – 2016

Advisors, Relations & Conflicts

Coauthor

Xintao Wu

2013 – 2022

Postdoc Advisor

Dejing Dou

2013 – 2016

Expertise

Privacy and Security

Present

Machine Learning

Present

Interpretable Deep Learning

Present

Publications

A Novel Adaptive Data Transformation for Contrastive Learning
YUCONG SHEN, Hai Phan, Frank Shih
- OpenReview Archive Direct Upload
- Readers: Everyone
Watermarking Degrades Alignment in Language Models: Analysis and Mitigation
Apurv Verma, Hai Phan, Shubhendu Trivedi
- Accepted by TMLR
- Readers: Everyone
Poisoning LLM-based Code Agents with Styles
Khang Tran, Yazan Boshmaf, Issa Khalil, Hai Phan, Ting Yu, Md Rizwan Parvez
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
PRPO: Paragraph-level Policy Optimization for Vision-Language Deepfake Detection
Tuan Nguyen, Naseem Khan, Khang Tran, Hai Phan, Issa Khalil
- ICLR 2026 Conference Desk Rejected Submission
- Readers: Everyone
$\delta$-STEAL: LLM Stealing Attack with Local Differential Privacy
Kieu Dang, Phung Lai, Hai Phan, yelong shen, Ruoming Jin, Abdallah Khreishah
- ACML 2025 Conference Track
- Readers: Everyone
Watermarking Degrades Alignment in Language Models: Analysis and Mitigation
Apurv Verma, Hai Phan, Shubhendu Trivedi
- WMARK@ICLR2025
- Readers: Everyone
Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)
Apurv Verma, Satyapriya Krishna, Sebastian Gehrmann, Madhavan Seshadri, Anu Pradhan, John A. Doucette, David Rabinowitz, Leslie Barrett, Tom Ault, Hai Phan
- Accepted by TMLR
- Readers: Everyone
How to Backdoor HyperNetwork in Personalized Federated Learning?
Phung Lai, Hai Phan, Issa Khalil, Abdallah Khreishah, Xintao Wu
- NeurIPS 2023 BUGS Poster
- Readers: Everyone
Model Transferring Attacks to Backdoor HyperNetwork in Personalized Federated Learning
Phung Lai, NhatHai Phan, Abdallah Khreishah, Issa Khalil, Xintao Wu
- 2022 (modified: 04 Mar 2022)
- CoRR 2022
- Readers: Everyone
User-Entity Differential Privacy in Learning Natural Language Models
Phung Lai, Tong Sun, Rajiv Jain, Franck Dernoncourt, Jiuxiang Gu, Nikolaos Barmpalios, Han Hu, Hai Phan
- 29 Sept 2021 (modified: 12 Oct 2025)
- ICLR 2022 Conference Withdrawn Submission
- Readers: Everyone

View all 53 publications

Co-Authors

View all 83 co-authors