Second year CS PhD student at UofT co-advised by Prof. Nicolas Papernot and Prof. Chris Maddison, supported by a Vanier Canada Graduate Scholarship.
Formerly a math specialist student (pure math) at UofT.

- "Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD"
__Anvith Thudi__, Hengrui Jia, Casey Meehan, Ilia Shumailov, Nicolas Papernot. Proceedings of the 33rd USENIX Security Symposium - "Better Sparsifiers for Directed Eulerian Graphs" Sushant Sachdeva,
__Anvith Thudi__, Yibin Zhao. Proceedings of the 51st EATCS International Colloquium on Automata, Languages and Programming - "From Differential Privacy to Bounds on Membership Inference: Less can be More"
__Anvith Thudi__, Ilia Shumailov, Franziska Boenisch, Nicolas Papernot. Transactions on Machine Learning Research - "Training Private Models That Know What They Don't Know" Stephan Rabanser,
__Anvith Thudi__, Abhradeep Thakurta, Krishnamurthy Dvijotham, Nicolas Papernot. Proceedings of the 37th Conference on Neural Information Processing Systems - "Proof-of-Learning is Currently More Broken Than You Think" Congyu Fang, Hengrui Jia,
__Anvith Thudi__, Mohammad Yaghini, Christopher A. Choquette-Choo, Natalie Dullerud, Varun Chandrasekaran, Nicolas Papernot. Proceedings of the 8th IEEE European Symposium on Security and Privacy - "On the Necessity of Auditable Algorithmic Definitions for Machine Unleaning" (slides)
__Anvith Thudi__, Hengrui Jia, Ilia Shumailov, Nicolas Papernot. Proceedings of the 31st USENIX Security Symposium - "Unrolling SGD: Understanding Factors Influencing Machine Unlearning" (slides)
__Anvith Thudi__, Gabriel Deza, Varun Chandrasekaran, Nicolas Papernot. Proceedings of the 7th IEEE European Symposium on Security and Privacy - "Proof of Learning: Definitions and Practice"Hengrui Jia, Mohammad Yaghini, Christopher A. Choquette-Choo, Natalie Dullerud,
__Anvith Thudi__, Varun Chandrasekaran, Nicolas Papernot. Proceedings of the 42nd IEEE Symposium on Security and Privacy

- "Finding Optimally Robust Data Mixtures via Concave Maximization"
__Anvith Thudi__, Chris J. Maddison - "Unlearnable Algorithms for In-context Learning" Andrei Muresanu,
__Anvith Thudi__, Michael R. Zhang, Nicolas Papernot - "Selective Classification via Neural Training Dynamics" Stephan Rabanser,
__Anvith Thudi__, Kimia Hamidieh, Adam Dziedzic, Nicolas Papernot - "SoK: Machine Learning Governance" Varun Chandrasekaran, Hengrui Jia,
__Anvith Thudi__, Adelin Travers, Mohammad Yaghini, Nicolas Papernot

A collection of expository essays written while studying C* algebras and their classification under Prof. George Elliott during my undergrad. The goal of these essays is to present the main prerequisite ideas for a particular problem in one relatively short document (as a sort of reference guide with a common theme).

- Category Theory and Classification
- The Classification of "Nice" C* Algebras
- The Atiyah-Singer Index Theorem (Note: indirectly motivated by a graduate course in Riemannian Geometry and the notion of index in terms of variations)
- Graphs and C* Algebras (Note: was taking a graduate course in combinatorics and hence had graphs on my mind)
- Irrational Rotational Algebras (Note: this is often the first concrete example on the classification of C* algebras one sees)