Being Patient and Persistent: Optimizing An Early Stopping Strategy for Deep Learning in Profiled Attacks
This work addresses a domain-specific issue for researchers in side-channel analysis by providing a more efficient evaluation method, though it is incremental as it builds on existing early stopping strategies.
The authors tackled the problem of evaluating deep learning models in side-channel attacks by proposing an early stopping algorithm that reliably identifies the optimal model state during training, resulting in convergence with fewer traces.
The absence of an algorithm that effectively monitors deep learning models used in side-channel attacks increases the difficulty of evaluation. If the attack is unsuccessful, the question is if we are dealing with a resistant implementation or a faulty model. We propose an early stopping algorithm that reliably recognizes the model's optimal state during training. The novelty of our solution is an efficient implementation of guessing entropy estimation. Additionally, we formalize two conditions, persistence and patience, for a deep learning model to be optimal. As a result, the model converges with fewer traces.