OMG-ATTACK: Self-Supervised On-Manifold Generation of Transferable Evasion Attacks
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 53 of its 71 references that are in the map. First posted on arXiv 5 Oct 2023.
Builds on
53 of 71 references.
References · 53
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2014Microsoft COCO: Common Objects in Contextcited by 17,608
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
- 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
- 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2022Generative Adversarial Networkscited by 5,627
- 2013Intriguing properties of neural networkscited by 5,155
38 more
- 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
- 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
- 2014Deep Learning Face Attributes in the Wildcited by 3,693
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
- 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
- 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
- 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,591
- 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
- 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,382
- 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
- 2016Adversarial Machine Learning at Scalecited by 936
- 2017Ensemble Adversarial Training: Attacks and Defensescited by 840
- 2015The Limitations of Deep Learning in Adversarial Settingscited by 790
- 2022data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Languagecited by 727
- 2017Evasion Attacks against Machine Learning at Test Timecited by 689
- 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 666
- 2020RobustBench: a standardized adversarial robustness benchmarkcited by 661
- 2017One pixel attack for fooling deep neural networkscited by 582
- 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 460
- 2018Generating Adversarial Examples with Adversarial Networkscited by 258
- 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 244
- 2021Enhancing the Transferability of Adversarial Attacks through Variance Tuningcited by 244
- 2019Adversarial Attacks and Defenses in Images, Graphs and Text: A Reviewcited by 237
- 2018Disentangling Adversarial Robustness and Generalizationcited by 172
- 2021On the Adversarial Robustness of Vision Transformerscited by 106
- 2020Contrastive Learning with Adversarial Examplescited by 91
- 2018On the Suitability of Lp-norms for Creating and Preventing Adversarial Examplescited by 58
- 2019Semantic Adversarial Attacks: Parametric Transformations That Fool Deep Classifierscited by 57
- 2020Viewmaker Networks: Learning Views for Unsupervised Representation Learningcited by 48
- 2018Guessing Smart: Biased Sampling for Efficient Black-Box Adversarial Attackscited by 46
- 2020AdvFlow: Inconspicuous Black-box Adversarial Attacks using Normalizing Flowscited by 36
- 2021A Review of Adversarial Attack and Defense for Classification Methodscited by 29
- 2021Grey-box Adversarial Attack And Defence For Sentiment Classificationcited by 28
- 2017Fine-grained Visual-textual Representation Learningcited by 27
- 2019Targeted Mismatch Adversarial Attack: Query with a Flower to Retrieve the Towercited by 26
- 2019AdvGAN++ : Harnessing latent layers for adversary generationcited by 20
- 2019On-manifold Adversarial Data Augmentation Improves Uncertainty Calibrationcited by 18
- 2018Gray-box Adversarial Trainingcited by 10
50 most cited of 53 All 53 (JSON)
Built on by
Citing papers per year: 2024: 1; 2025: 0; 2026: 1.
2 papers.