Karthik Garimella

Karthik Garimella

Bio

I am a final year ECE PhD candidate at New York University advised by Brandon Reagen. I also collaborate with Siddharth Garg. My work sits at the intersection of machine learning systems, compilers, and computer architecture, with a focus on privacy-preserving inference using Fully Homomorphic Encryption (FHE). I built EinHops, which brings an einsum-style programming abstraction to FHE and helped develop Orion, an encrypted neural inference framework. During summer 2024, I interned at NVIDIA Research in the Programming Systems and Applications group.

Before NYU, I earned an MS in Computer Engineering from Washington University in St. Louis where I worked on self-driving vehicles and adversarial machine learning. I also hold a BA in Physics from Hendrix College.

I am currently on the job market looking for research engineer and scientist roles. Please feel free to reach out!

Publications

EinHops: Einsum Notation for Expressive Homomorphic Operations on RNS-CKKS Tensors
Karthik Garimella, Austin Ebel, Brandon Reagen
Workshop on Applied Homomorphic Encryption @ ACM CCS, 2025
[arXiv] [code]

Orion: A Fully Homomorphic Encryption Framework for Deep Learning
Austin Ebel, Karthik Garimella, Brandon Reagen
ASPLOS, 2025, Best Paper Award
[arXiv] [code]

Characterizing and Optimizing End-to-End Systems for Private Inference
Karthik Garimella, Zahra Ghodsi, Nandan Kumar Jha, Siddharth Garg, Brandon Reagen
ASPLOS, 2023 example example example
[arXiv] [code] [poster]

CryptoNite: Revealing the Pitfalls of End-to-End Private Inference at Scale
Karthik Garimella, Nandan Kumar Jha, Zahra Ghodsi, Siddharth Garg, Brandon Reagen
arxiv pre-print, 2021
[arXiv]

Sisyphus: A Cautionary Tale of Using Low-Degree Polynomial Activations in Privacy-Preserving Deep Learning
Karthik Garimella, Nandan Kumar Jha, Brandon Reagen
Privacy Preserving Machine Learning Workshop @ ACM CCS, 2021
[arXiv] [code] [poster]

Attacking Vision-based Perception in End-to-End Autonomous Driving Models
Adith Boloor, Karthik Garimella, Xin He, Christopher Gill, Yevgeniy Vorobeychik, Xuan Zhang
Journal of Systems Architecture, 2020
[arXiv] [code]

CARLA Autonomous Driving Challenge 2019
Adith Boloor, Karthik Garimella, Jinghan Yang, Christopher Gill, Yevgeniy Vorobeychik, Ayan Chakrabarti, Xuan Zhang
Invited talk at CVPR, 2019
[CVPR workshop] [code]

Teaching

Head Graduate Teaching Assistant - Deep Learning Spring 2023 @ NYU ECE
Head Graduate Teaching Assistant - Computer Architecture Fall 2023 @ NYU ECE