# Being Patient and Persistent: Optimizing An Early Stopping Strategy for Deep Learning in Profiled Attacks

arXiv: https://arxiv.org/abs/2111.14416 · HTML: https://mlsanity.com/paper/2111.14416/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 18 references that are in the map.
- First posted on arXiv 29 Nov 2021.

## Builds on (most cited first, 2 of 2)

- [Opening the Black Box of Deep Neural Networks via Information](https://mlsanity.com/paper/1703.00810/) (2017)
- [The uncertainty of Side-Channel Analysis: A way to leverage from heuristics](https://mlsanity.com/paper/2006.12810/) (2020)

## Built on by (most cited first, 1 of 1)

- [Playing with blocks: Toward re-usable deep learning models for side-channel profiled attacks](https://mlsanity.com/paper/2203.08448/) (2022)

## Abstract (arXiv)

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.