Brain Programming is Immune to Adversarial Attacks: Towards Accurate and Robust Image Classification using Symbolic Learning
Not on the map. Why?
Abstract (arXiv)
In recent years, the security concerns about the vulnerability of Deep Convolutional Neural Networks (DCNN) to Adversarial Attacks (AA) in the form of small modifications to the input image almost invisible to human vision make their predictions untrustworthy. Therefore, it is necessary to provide robustness to adversarial examples in addition to an accurate score when developing a new classifier. In this work, we perform a comparative study of the effects of AA on the complex problem of art media categorization, which involves a sophisticated analysis of features to classify a fine collection of artworks. We tested a prevailing bag of visual words approach from computer vision, four state-of-the-art DCNN models (AlexNet, VGG, ResNet, ResNet101), and the Brain Programming (BP) algorithm. In this study, we analyze the algorithms' performance using accuracy. Besides, we use the accuracy ratio between adversarial examples and clean images to measure robustness. Moreover, we propose a statistical analysis of each classifier's predictions' confidence to corroborate the results. We confirm that BP predictions' change was below 2% using adversarial examples computed with the fast gradient sign method. Also, considering the multiple pixel attack, BP obtained four out of seven classes without changes and the rest with a maximum error of 4% in the predictions. Finally, BP also gets four categories using adversarial patches without changes and for the remaining three classes with a variation of 1%. Additionally, the statistical analysis showed that the predictions' confidence of BP were not significantly different for each pair of clean and perturbed images in every experiment. These results prove BP's robustness against adversarial examples compared to DCNN and handcrafted features methods, whose performance on the art media classification was compromised with the proposed perturbations.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 26 of its 93 references that are in the map. First posted on arXiv 1 Mar 2021.
Builds on
26 of 93 references.
References · 26
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2013Intriguing properties of neural networkscited by 5,114
- 2016Adversarial Machine Learning at Scalecited by 934
- 2016Universal adversarial perturbationscited by 774
- 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
- 2017One pixel attack for fooling deep neural networkscited by 579
- 2017Adversarial Patchcited by 514
- 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
- 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
- 2017MagNet: a Two-Pronged Defense against Adversarial Examplescited by 268
14 more
- 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 243
- 2017Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradientscited by 236
- 2019Adversarial Attacks and Defenses in Images, Graphs and Text: A Reviewcited by 234
- 2016Improving the Robustness of Deep Neural Networks via Stability Trainingcited by 156
- 2014Towards Deep Neural Network Architectures Robust to Adversarial Examplescited by 146
- 2018Is Robustness the Cost of Accuracy? -- A Comprehensive Study on the Robustness of 18 Deep Image Classification Modelscited by 135
- 2013Recognizing Image Stylecited by 64
- 2019The Limitations of Adversarial Training and the Blind-Spot Attackcited by 63
- 2017Evolving Deep Convolutional Neural Networks for Image Classificationcited by 54
- 2017Defense against Universal Adversarial Perturbationscited by 48
- 2018The Shape of Art History in the Eyes of the Machinecited by 33
- 2013Unsupervised Feature Learning by Deep Sparse Codingcited by 4
- 2017Picasso, Matisse, or a Fake? Automated Analysis of Drawings at the Stroke Level for Attribution and Authenticationcited by 4
- 2020A Deep Genetic Programming based Methodology for Art Media Classification Robust to Adversarial Perturbationscited by 1
Built on by
Citing papers per year: 2022: 2.
2 papers.