I’m a PhD candidate in Computer Science at the University of California, Davis advised by Professor Magdalena Wojcieszak. My research interests involve the privacy, societal, and safety implications of online algorithmic systems.

News

2025 Mar Passed the Doctoral Qualifying Exam and advanced to PhD candidacy.
2024 Nov Nudging the Recommendation Algorithm Increases News Consumption and Diversity on YouTube was accepted at PNAS Nexus.
2024 Oct Invited to attend the MPK Meta Research Day at their Menlo Park HQ.
2024 Sep Presented at Trust & Safety Research Conference at Stanford University.
2024 May Awarded the GGCS Research Fellowship ($18,000) for Summer 2024.
2023 Sep Attended the Trust & Safety Research Conference at Stanford University.
2023 Sep Attended the third annual ProperData Symposium at Northeastern University.
2023 Jun Awarded the GGCS Research Fellowship ($18,000) for Summer 2023.
2023 Jun Auditing YouTube's Recommendation System for Ideologically Congenial, Extreme, and Problematic Recommendations was accepted in PNAS.
2023 Mar Awarded the GGCS Research Fellowship ($7,177) for Spring 2023.
2022 Dec Attended the second annual ProperData Symposium at UC Irvine.
2022 Nov Attended the UC Noyce Initiative Symposium '22 at UC Santa Barbara.
2022 Oct Presented at the UC Davis Noyce Workshop.
2022 Aug Research featured in the UC Davis College of Engineering News.
2022 Jun Presented at the Politics and Computational Social Science (PaCSS) conference at Harvard University.
2022 Jun Participated and presented at the Summer Institute in Computational Social Science (SICSS) at the University of Pennsylvania.
2022 Jun Attended the International AAAI Conference on Web and Social Media '22 (ICWSM) in Atlanta.
2022 May Attended the IEEE Symposium on Security & Privacy '22 (Oakland) in San Francisco.
2021 Nov Attended the ProperData Symposium at UC Irvine.
2021 Oct HARPO: Learning to Subvert Online Behavioral Advertising was accepted at NDSS'22.
2021 Mar Left TPI lab and joined the PhD program at UC Davis.

Publications

"Whose Side Are You On?" Estimating Ideology of Political and News Content Using Large Language Models and Few-shot Demonstration Selection

Muhammad Haroon, Magdalena Wojcieszak, Anshuman Chhabra

arXiv pre-print, 2025

Re-ranking Using Large Language Models for Mitigating Exposure to Harmful Content on Social Media Platforms

Rajvardhan Oak, Muhammad Haroon, Claire Jo, Magdalena Wojcieszak, Anshuman Chhabra

arXiv pre-print, 2025

Nudging the Recommendation Algorithm Increases News Consumption and Diversity on YouTube

Xudong Yu, Muhammad Haroon, Ericka Menchen-Trevino, Magdalena Wojcieszak

PNAS Nexus, 2024

Auditing YouTube's Recommendation System for Ideologically Congenial, Extreme, and Problematic Recommendations

Muhammad Haroon, Magdalena Wojcieszak, Anshuman Chhabra, Xin Liu, Prasant Mohapatra, Zubair Shafiq

Proceedings of the National Academy of Sciences (PNAS), 2023

HARPO: Learning to Subvert Online Behavioral Advertising

Jiang Zhang, Konstantinos Psounis, Muhammad Haroon, Zubair Shafiq

The Network and Distributed System Security Symposium (NDSS), 2022

Avengers Ensemble! Improving Transferability of Authorship Obfuscation

Muhammad Haroon, Fareed Zaffar, Padmini Srinivasan, Zubair Shafiq

arXiv pre-print, 2021

Talks + Podcasts

User or Algorithm? Investigating what drives congenial consumption on YouTube

Communication Horizons Conference, UC Davis, 2024

YouTube, The Great Radicalizer?

Politics and Computational Social Science Conference (PaCSS), Harvard University
Summer Institute in Computation Social Science (SICSS), University of Pennsylvania
, 2022

How Social Media Algorithms Can Foster Political Radicalization

The Backdrop - A UC Davis Podcast, 2022

Offensive Privacy to Counter AdTech Surveillance

Nothing to Hide - A Data Privacy Podcast, 2022