Radhika Garg

I am a Ph.D. candidate in Computer Science at Northwestern University, advised by Dr. Xiao Wang, graduating late 2025. My research is in applied cryptography, with a focus on making secure computation practical and deployable.

My work spans three threads. I built Smaug, an LLVM-native compiler that transforms standard C++ and Rust into MPC-ready oblivious code, compiling up to 1240× faster than prior tools while matching or outperforming their output circuit quality. I have designed scalable MPC protocols for real-world privacy — including a mixed-mode framework supporting 100+ parties and an efficient noise sampling protocol for differentially private federated learning. I am currently working on two projects: Noisette, a unified framework for certifying differential privacy mechanisms across discrete and continuous distributions, and threshold signature schemes compatible with the deployed NIST FALCON standard.

During my internship at Meta FAIR (AI4Crypto) with Dr. Kristin Lauter, I built transformer-based distinguishers targeting the EA-LPN hardness assumption, bridging deep learning and cryptographic analysis.

I received my B.Tech. in Computer Science from the Indian Institute of Technology Roorkee in 2022.