AutoLike

How can researchers audit recommendation systems when the algorithms are hidden from view? Hieu Le joins Kyle Polich to discuss Auto-Like, a reinforcement learning framework that systematically explores how platforms like TikTok personalize content feeds. The conversation covers recommendation transparency, black-box auditing, and the future of platform accountability.

Guest

Hieu Le: I am currently serving as a Senior Technologist at the Federal Trade Commission’s Office of Technology, where I leverage my expertise on privacy, automated systems, and applied machine learning to further the agency’s mission to protect consumers and promote fair competition. Previously, I was a Postdoctoral Research Fellow within Roya Ensafi’s Censored Planet Lab in the Computer Science and Engineering (CSE) School at the University of Michigan, Ann Arbor. I collaborated on projects that examined the impact of geoblocking on citizens in sanctioned states as well as the development of machine learning and outlier detection methodologies to identify censorship events and content. I received my PhD in Electrical Engineering and Computer Science (EECS) at UC Irvine and was advised by Athina Markopoulou and part of the ProperData NSF Frontier project. My doctoral studies centers on privacy and networking to improve the (1) transparency of data collection practices of different platforms such as the web, smart TVs and Oculus VR; and the (2) control of data collection by designing frameworks and methodologies to automate the pain-points of privacy-enhancing technologies (PETs) that block advertising and tracking on the web.