I'm a Ph.D. candidate in theoretical computer science at Boston University, under the excellent supervision of Ran Canetti. For the spring semester of 2023, I'm visiting the Simons Institute for the theory of computing at UC Berkeley, where I'll be a full time participant of the Meta Complexity program.
I research topics in the intersection of cryptography and computational learning theory.
More about my research.
I have additional interests in pseudo-randomness and (meta-)complexity theory, as well as security issues in machine learning.
Papers
- "New Approaches to Heuristic PAC-Learning from Non-Existence of PRFs"
Marco Carmosino and Ari Karchmer
Forthcoming (in submission), 2022 - "Theoretical Limits of Provable Security Against Model Extraction by Efficient Observational Defenses"
Ari Karchmer
Conference version in the IEEE Conference on Secure and Trustworthy Machine Learning (SATML), February 2023 -
"Covert Learning: How to Learn with an Untrusted Intermediary"
Ran Canetti and Ari Karchmer
Conference version in Proceedings of the 19th International Theory of Cryptography Conference (TCC), 2021
*Invited to Journal of Cryptology
*I wrote about this work on a blog post for the BU center for reliable information systems and cybersecurity (RISCS)
Select Talks
Teaching Fellowships