Gabriele Farina 2024 Early Career Fellow
Hard Problem Solved AI’s continually evolving safety and security, robustness, performance, output challenges and other shortcomings that may cause harm or erode public trust of AI systems, especially in safety-critical applications and uses where societal stakes and potential for societal harm are high.

Gabriele Farina is an Assistant Professor at MIT EECS and LIDS. His research combines techniques and notions of strategic behavior from game theory together with modern tools from machine learning, optimization, and statistics to construct state-of-the-art methods to compute optimal strategies for multiagent interactions. Professor Farina received his Ph.D. in Computer Science from Carnegie Mellon University, and his work has been recognized with several awards, including a Best Paper Award at NeurIPS’20 and an Outstanding Paper Honorable Mention at ICLR’23. His dissertation was recognized with the 2023 ACM SIGecom Doctoral Dissertation Award and one of the two 2023 ACM Dissertation Award Honorable Mentions, among others.

AI2050 Project

In imperfect-information games—a general setting that includes recreational games, auctions, and information design problems—optimal solutions can be highly uninterpretable, randomized, and hard to verify. In turn, this makes them more prone to misapplication or exploitation. This project aims to devise theoretical and practical solutions to balance interpretability and strategic soundness, addressing fundamental blind spots in our current understanding and investigating the application of this technology on testbeds spanning both auction design and security games.