OMG-Attack: Self-Supervised On-Manifold Generation of Transferable Evasion Attacks
Open Access
- 2 October 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3698-3708
Abstract
Evasion Attacks (EA) are used to test the robustness of trained neural networks by distorting input data to misguide the model into incorrect classifications. Creating these attacks is a challenging task, especially with the ever increasing complexity of models and datasets. In this work, we introduce a self-supervised, computationally economical method for generating adversarial examples, designed for the unseen black-box setting. Adapting techniques from representation learning, our method generates on-manifold EAs that are encouraged to resemble the data distribution. These attacks are comparable in effectiveness compared to the state-of-the-art when attacking the model trained on, but are significantly more effective when attacking unseen models, as the attacks are more related to the data rather than the model itself. Our experiments consistently demonstrate the method is effective across various models, unseen data categories, and even defended models, suggesting a significant role for on-manifold EAs when targeting unseen models.Keywords
All Related Versions
This publication has 44 references indexed in Scilit:
- Towards Evaluating the Robustness of Neural Networks2017
- DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks2016
- Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles2016
- Deep Residual Learning for Image Recognition2016
- The Limitations of Deep Learning in Adversarial Settings2016
- Deep Learning Face Attributes in the Wild2015
- Microsoft COCO: Common Objects in Context2014
- Representation Learning: A Review and New PerspectivesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Evasion Attacks against Machine Learning at Test Time2013
- Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognitionNeural Networks, 2012