ABOUT
I am currently a postdoctoral researcher at Northeastern's Institute for Experiential AI. I work with the Responsible AI team and spend a lot of time thinking about safety and evaluations for LLMs these days.
I received my Ph.D. in computer science at Northeastern University, where I was fortunate to be advised by Alan Mislove. My dissertation focused on measuring discrimination and harmful outcomes due to personalization in online advertising. I am a recipient of Northeastern's Outstanding Graduate Student in Research award.
During grad school, I interned at Oracle Labs, where I worked with the Machine Learning Research Group on measuring linguistic biases in LLMs in connection to model scale. I also interned at Intel, where I worked on generating model cards and explanations for their repository of ML models.
Before Northeastern, I got my master's degree in computer science at Saarland University. At Saarland, I was a member of Krishna Gummadi's Networked Systems group at the Max Planck Institute for Software Systems.
PUBLICATIONS
-
Problematic Advertising and its Disparate Exposure on Facebook
Muhammad Ali, Angelica Goetzen, Alan Mislove, Elissa M. Redmiles, Piotr Sapiezynski
Proceedings of the 32nd USENIX Security Symposium
Anaheim, CA, August 2023.
[arXiv version]
-
All Things Unequal: Measuring Disparity of Potentially Harmful Ads on Facebook
Muhammad Ali, Angelica Goetzen, Alan Mislove, Elissa M. Redmiles, Piotr Sapiezynski
Proceedings of the 6th Workshop on Technology and Consumer Protection (ConPro '22)
at IEEE S&P Symposium, San Francisco, CA, May 2022.
-
Measuring and Mitigating Bias and Harm in Personalized Advertising
Muhammad Ali
Proceedings of the 15th ACM Conference on Recommender Systems (RecSys '21),
Amsterdam, The Netherlands, September 2021. (Extended Abstract)
-
Ad Delivery Algorithms: The Hidden Arbiters of Political Messaging
Muhammad Ali*, Piotr Sapiezynski*, Aleksandra Korolova, Alan Mislove, Aaron Rieke
Proceedings of the 14th ACM Conference on Web Search and Data Mining (WSDM '21),
Virtual, March 2021.
-
Discrimination through optimization: How Facebook's ad delivery can lead to skewed outcomes
Muhammad Ali*, Piotr Sapiezynski*, Miranda Bogen, Aleksandra Korolova, Alan Mislove, Aaron Rieke
Proceedings of the ACM Conference on Computer Supported Cooperative Work (CSCW '19) Austin, TX, USA, November 2019.
Diversity and Inclusion Award, Honorable Mention
Press: Vox, The Economist, WIRED, The Intercept, MIT Technology Review, The Verge, Motherboard, and erm... Breitbart -
Potential for Discrimination in Online Targeted Advertising
Till Speicher, Muhammad Ali, Giridhari Venkatadri, George Arvanitakis, Krishna P. Gummadi, Patrick Loiseau, and Alan Mislove
Proceedings of the 1st Conference on Fairness, Accountability, and Transparency (FAT*),
New York, NY, February 2018.
Best Paper Nominee
-
On Quantifying Knowledge Segregation in Society
Abhijnan Chakraborty, Muhammad Ali, Saptarshi Ghosh, Niloy Ganguly, and Krishna P. Gummadi
Proceedings of the FATREC Workshop on Responsible Recommendation (colocated with RecSys 2017), Como, Italy, August 2017.
THESES
-
Measuring the Harms of Personalization through Advertising
Muhammad Ali
Ph.D. Thesis, Northeastern University, Boston, MA, October 2023. -
Measuring Bias in Facebook's Ad-Targeting Attributes
Muhammad Ali
Master's Thesis, Saarland University, Saarbrücken, Germany, August 2018.
MISC.
Back home in Lahore, Pakistan, I did my undergrad in computer science at FAST-NUCES. My Twitter handle is the name of the neighborhood in Lahore where I grew up. I live in Cambridge, MA with my wife, whose love, wisdom, and care work make graduate school easier.
The font for all headings on this homepage is inspired by Ed Ruscha W.E.B. Du Bois – who used data visualizations as a way to communicate social injustices.
Outside of work, I enjoy reading, indie video games and music. I am a student of the tabla – it's something I picked up very late in life but am currently refusing to give up. On difficult days, I like to re-read Bill Watterson's commencement speech.