# Does Saliency-Based Training bring Robustness for Deep Neural Networks in Image Classification?

Source: [Does Saliency-Based Training bring Robustness for Deep Neural Networks in Image Classification?](<https://www.sota2.com/research/paper/68fa6fea1e209131cea48234>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:30:17.231Z

Authors: Ali Karkehabadi

Published: 2023-06-28T22:20:19.000Z

## Abstract

Deep Neural Networks are powerful tools to understand complex patterns and making decisions. However, their black-box nature impedes a complete understanding of their inner workings. While online saliency-guided training methods try to highlight the prominent features in the model's output to alleviate this problem, it is still ambiguous if the visually explainable features align with robustness of the model against adversarial examples. In this paper, we investigate the saliency trained model's vulnerability to adversarial examples methods. Models are trained using an online saliency-guided training method and evaluated against popular algorithms of adversarial examples. We quantify the robustness and conclude that despite the well-explained visualizations in the model's output, the salient models suffer from the lower performance against adversarial examples attacks.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2306.16581>)

[PDF](<https://arxiv.org/pdf/2306.16581.pdf>)