Investigating Human-Identifiable Features Hidden in Adversarial Perturbations

Dennis Yuren Menn, Tzu-hsun Feng, Sriram Vishwanath, Hung-yi Lee

Primary Area: societal considerations including fairness, safety, privacy

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Adversarial Attack, Computer Vision, Neural Network

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: We demonstrate that adversarial perturbations contain human-identifiable features, which are responsible for a neural network’s misclassification.

Abstract: Neural networks perform exceedingly well across various machine learning tasks but are not immune to adversarial perturbations. This vulnerability has implications for real-world applications. While much research has been conducted, the underlying reasons why neural networks fall prey to adversarial attacks are not yet fully understood. Central to our study, which explores up to five attack algorithms across three datasets, is the identification of human-identifiable features in adversarial perturbations. Additionally, we uncover two distinct effects manifesting within human-identifiable features. Specifically, the masking effect is prominent in untargeted attacks, while the generation effect is more common in targeted attacks. Using pixel-level annotations, we extract such features and demonstrate their ability to compromise target models. In addition, our findings indicate a notable extent of similarity in perturbations across different attack algorithms when averaged over multiple models. This work also provides insights into phenomena associated with adversarial perturbations, such as transferability and model interpretability. Our study contributes to a deeper understanding of the underlying mechanisms behind adversarial attacks and offers insights for the development of more resilient defense strategies for neural networks.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 4550