2025-01-14-liu25c.md

title	booktitle	year	volume	series	month	publisher	pdf	url	software	openreview	abstract	layout	issn	id	tex_title	firstpage	lastpage	page	order	cycles	bibtex_editor	editor	bibtex_author	author	date	address	container-title	genre	issued	extras
The data-driven transferable adversarial space	Proceedings of the 16th Asian Conference on Machine Learning	2025	260	Proceedings of Machine Learning Research	0	PMLR	https://raw.githubusercontent.com/mlresearch/v260/main/assets/liu25c/liu25c.pdf	https://proceedings.mlr.press/v260/liu25c.html	https://github.com/flavie-yuan-liu/Adversarial-Space.git	aXiGYaY3KZ	Deep Neural Network (DNN) models are vulnerable to deception through the intentional addition of imperceptible perturbations to benign examples, posing a significant threat to security-sensitive applications. To address this, understanding the underlying causes of this phenomenon is crucial for developing robust models. A key research area involves investigating the characteristics of adversarial directions, which have been found to be perpendicular to decision boundaries and associated with low-density regions of the data. Existing research primarily focuses on adversarial directions for individual examples, while decision boundaries and data distributions are inherently dataset-dependent. This paper explores the space of adversarial perturbations within a dataset. Specifically, we represent adversarial perturbations as a linear combination of adversarial directions, followed by a non-linear projection. Using the proposed greedy algorithm, we train the adversarial space spanned by the set of adversarial directions. Experiments on Cifar10 and ImageNet substantiate the existence of the adversarial space as an embedded space within the entire data space. Furthermore, the learned adversarial space enables statistical analysis of decision boundaries. Finally, we observe that the adversarial space learned on one DNN model is model-agnostic, and that the adversarial space learned on a vanilla model is a subset of that learned on a robust model, implicating data distribution as the underlying cause of adversarial examples.	inproceedings	2640-3498	liu25c	The data-driven transferable adversarial space	1144	1159	1144-1159	1144	false	Nguyen, Vu and Lin, Hsuan-Tien	given family Vu Nguyen given family Hsuan-Tien Lin	Liu, Yuan and Canu, Stephane	given family Yuan Liu given family Stephane Canu	2025-01-14		Proceedings of the 16th Asian Conference on Machine Learning	inproceedings	date-parts 2025 1 14