# The Importance of Image Interpretation: Patterns of Semantic Misclassification in Real-World Adversarial Images

arXiv: https://arxiv.org/abs/2206.01467 · HTML: https://mlsanity.com/paper/2206.01467/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 12 references that are in the map.
- First posted on arXiv 3 Jun 2022.

## Builds on (most cited first, 8 of 8)

- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [The Limitations of Deep Learning in Adversarial Settings](https://mlsanity.com/paper/1511.07528/) (2015)
- [Improving Transferability of Adversarial Examples with Input Diversity](https://mlsanity.com/paper/1803.06978/) (2018)
- [Delving into Transferable Adversarial Examples and Black-box Attacks](https://mlsanity.com/paper/1611.02770/) (2016)
- [Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks](https://mlsanity.com/paper/1904.02884/) (2019)
- [On Success and Simplicity: A Second Look at Transferable Targeted Attacks](https://mlsanity.com/paper/2012.11207/) (2020)
- [Towards Large yet Imperceptible Adversarial Image Perturbations with Perceptual Color Distance](https://mlsanity.com/paper/1911.02466/) (2019)
- [Perturbing Across the Feature Hierarchy to Improve Standard and Strict Blackbox Attack Transferability](https://mlsanity.com/paper/2004.14861/) (2020)

## Abstract (arXiv)

Adversarial images are created with the intention of causing an image classifier to produce a misclassification. In this paper, we propose that adversarial images should be evaluated based on semantic mismatch, rather than label mismatch, as used in current work. In other words, we propose that an image of a "mug" would be considered adversarial if classified as "turnip", but not as "cup", as current systems would assume. Our novel idea of taking semantic misclassification into account in the evaluation of adversarial images offers two benefits. First, it is a more realistic conceptualization of what makes an image adversarial, which is important in order to fully understand the implications of adversarial images for security and privacy. Second, it makes it possible to evaluate the transferability of adversarial images to a real-world classifier, without requiring the classifier's label set to have been available during the creation of the images. The paper carries out an evaluation of a transfer attack on a real-world image classifier that is made possible by our semantic misclassification approach. The attack reveals patterns in the semantics of adversarial misclassifications that could not be investigated using conventional label mismatch.