Huzaifa Arif
Hi My name is Huzaifa Arif and I am a third year PhD student at Rensselaer Polytechnic Institute. My advisor is Dr. Alex Gittens.
Research Interests
My primary research focus is on Trustworthy Machine Learning within federated settings. I have contributed to research in model reprogramming, group fairness, and adversarial attacks on foundation models. Currently, I am developing algorithms to address data leakage in these models. If your research interests align with mine, please feel free to reach out.
CV
Link to my CV
Experience
Lawrence Livermore National Labortary - Livermore, CA Data Science Intern - May 2024–Aug 2024
IBM T.J Watson Research Center - Yorktown Heights, NY
AI Research Extern - Trustworthy AI - Jun 2023–Aug 2023
Mentor: Pin-Yu Chen, Keerthiram Murugesan, Payel Das
IBM T.J Watson Research Center - Yorktown Heights, NY
AI Research Extern - Trustworthy AI - Jun 2022–Aug 2022
Mentor: Pin-Yu Chen
Education
Rensselaer Polytechnic Institute - Troy, NY
Electrical and Computer Systems Engineering Ph.D - 3.95 GPA - Jan 2021–
Lahore University of Management Sciences - Lahore, Pakistan
Electrical Engineering B.S.
Publications
Reprogrammable-FL: Improving Utility-Privacy Tradeoff in Federated Learning via Model Reprogramming
- Conference: IEEE Conference on Secure and Trustworthy Machine Learning, February 2023
- Authors: Huzaifa Arif, Alex Gittens, Pin-Yu Chen Talk Code Paper
Preprints
DP-Compressed VFL is secure for Model Inversion Attacks
Additional Research Work
- Our adaptation of Hypergradient Descent found at Project
- PhD Qualifier Report : Paper
Patents
- Differentially Private Federated Learning using Model Reprogramming (Huzaifa Arif,Pin-Yu-Chen, Bo Wu, Zhengfang Chen, Chuang Gan) (US20240256894A1)
Reviewer Experience
- International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2023)
- Artificial Intelligence and Statistics (AISTATS) 2023
- IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2023)
Recent News
- Aug 2024: Our patent Reprogrammable FL got accepted
- May 2024: Started my internship at Lawrence Livermore National Labortary
- May 2024 : Submitted my work based on composite gradient based bias mitigation algorithm in Federated Learning to Neurips 2024
- May 2024: Submitted work in IBM Internship (Data Leakage in Residual Network)) to Neurips 2024
- May 2023: Started my IBM internship with mentors Pin-Yu Chen and Keerthiram Murugesan
- Feb 2023: Filed a patent of Reprogrammable FL with IBM (under review)
- Oct 2022: Internship work (Reprogrammable FL) accepted at SATML 2023
- Aug 2022: Moved to research group of Dr. Alex Gittens
- May 2022: Started my IBM internship with mentor Pin-Yu Chen
- Apr 2022: Passed my PhD Qualification Exam (Rank: Top-5)
- Apr 2022: Work done with Dr. Stacy Patterson. Preprint available : DP-Compressed VFL is secure for Model InversionAttacks
- Jan 2021: Joined RPI as a PhD student
Contact
Email: arifh@rpi.edu ; huzaifaarif20@gmail.com (Phone) : 518-961 8482