Security, Privacy, Cryptography × Machine Learning

Harish
Karthikeyan

Senior Research Scientist
J.P. Morgan AI Research & AlgoCRYPT Center of Excellence
277 Park Avenue, New York, NY · he / him / his

Designing privacy-enhancing technologies for AI/ML systems — with a focus on federated learning, secure aggregation, and cryptographic protocols for multi-agent systems.

Publications Get in Touch

Ph.D. NYU ’22

M.S. Columbia ’16

B.Tech NIT Trichy ’15

Updates

News & Announcements

2026 New TAPAS: Efficient Two-Server Asymmetric Private Aggregation Beyond Prio(+) accepted at Theory and Practice of Multi-party Computation (TPMPC) 2026

2026 New Invited to give a talk on Secure Aggregation and Federated Learning at Flower AI Summit, London, 2026.

2026 New Serving as Reviewer for NeurIPS 2026.

2026 New Serving on the Program Committee of ACM CCS 2026.

2026 New Updatable Public Key Encryption based on Hidden Subgroup Membership accepted at Financial Cryptography 2026, Saint Kitts & Nevis.

Dec 2025 AgentCrypt and HashMark presented at NeurIPS 2025 Workshops.

Oct 2025 Armadillo — single-server secure aggregation with robustness against malicious clients — presented at ACM CCS 2025, Taipei.

2025 OPA: One-shot Private Aggregation with Single Client Interaction accepted at CRYPTO 2025.

Focus Areas

Research Interests

01 — Privacy-Preserving FL

Federated Learning & Secure Aggregation

Designing protocols for distributed ML that protect individual contributions — including LWE-based masking, Count-Min Sketch deduplication, and attack-resistant aggregation.

02 — Cryptographic Protocols

Applied Cryptography

Identity-based encryption, fully homomorphic encryption, verifiable secret sharing, updatable PKE, and post-quantum lattice-based constructions.

03 — Multi-Agent Systems

Secure AI Agent Collaboration

Cryptographic frameworks enabling privacy-preserving collaboration between AI agents, including IBE and FHE-based architectures such as AgentCrypt.

Biography

About

I am a Senior Research Scientist at J.P. Morgan AI Research and the J.P. Morgan AlgoCRYPT Center of Excellence. My research sits at the intersection of cryptography and machine learning, focused on privacy-enhancing technologies for AI/ML systems.

I earned my Ph.D. in Computer Science in 2022 from New York University under Yevgeniy Dodis, with a dissertation titled "Cryptography: From Practice to Theory." During doctoral studies, I collaborated with Antigoni Polychroniadou on privacy-preserving consensus.

Previously, I received an M.S. from Columbia University (with Allison Bishop) and a B.Tech from NIT Trichy. I also interned at Amazon Seattle (2016) building an ML-based trending algorithm for the Bestseller team.

Education

Doctor of Philosophy, 2022

New York University, Courant Institute

Advisor: Yevgeniy Dodis

Master of Science

Columbia University

Advisor: Allison Bishop

B.Tech — First Class with Distinction

National Institute of Technology Trichy

Advisor: Kunwar Singh