# Not All Adversarial Examples Require a Complex Defense: Identifying Over-optimized Adversarial Examples with IQR-based Logit Thresholding

Source: [Not All Adversarial Examples Require a Complex Defense: Identifying Over-optimized Adversarial Examples with IQR-based Logit Thresholding](<https://www.sota2.com/research/paper/68fa661e1e209131cea0e75a>)

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

Data updated: 2025-10-25T21:43:30.383Z

Authors: Utku Ozbulak, Arnout Van Messem, Wesley De Neve

Published: 2019-07-30T05:46:49.000Z

## Abstract

Detecting adversarial examples currently stands as one of the biggest challenges in the field of deep learning. Adversarial attacks, which produce adversarial examples, increase the prediction likelihood of a target class for a particular data point. During this process, the adversarial example can be further optimized, even when it has already been wrongly classified with 100% confidence, thus making the adversarial example even more difficult to detect. For this kind of adversarial examples, which we refer to as over-optimized adversarial examples, we discovered that the logits of the model provide solid clues on whether the data point at hand is adversarial or genuine. In this context, we first discuss the masking effect of the softmax function for the prediction made and explain why the logits of the model are more useful in detecting over-optimized adversarial examples. To identify this type of adversarial examples in practice, we propose a non-parametric and computationally efficient method which relies on interquartile range, with this method becoming more effective as the image resolution increases. We support our observations throughout the paper with detailed experiments for different datasets (MNIST, CIFAR-10, and ImageNet) and several architectures.

## 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/1907.12744>)

[PDF](<https://arxiv.org/pdf/1907.12744.pdf>)
