3 papers
cs.LG2026
Learning to Query History: Nonstationary Classification via Learned Retrieval
Jimmy Gammell, Bishal Thapaliya, Yoon Jung +3
Nonstationarity is ubiquitous in practical classification settings, leading deployed models to perform poorly even when they generalize well to holdout sets available at training t…
cs.LG2025
Learning to Localize Leakage of Cryptographic Sensitive Variables
Jimmy Gammell, Anand Raghunathan, Abolfazl Hashemi +1
While cryptographic algorithms such as the ubiquitous Advanced Encryption Standard (AES) are secure, *physical implementations* of these algorithms in hardware inevitably 'leak' se…
cs.LG2024
Power side-channel leakage localization through adversarial training of deep neural networks
Jimmy Gammell, Anand Raghunathan, Kaushik Roy
Supervised deep learning has emerged as an effective tool for carrying out power side-channel attacks on cryptographic implementations. While increasingly-powerful deep learning-ba…