Brightness-Restricted Adversarial Attack Patch (2307.00421v1)
Abstract: Adversarial attack patches have gained increasing attention due to their practical applicability in physical-world scenarios. However, the bright colors used in attack patches represent a significant drawback, as they can be easily identified by human observers. Moreover, even though these attacks have been highly successful in deceiving target networks, which specific features of the attack patch contribute to its success are still unknown. Our paper introduces a brightness-restricted patch (BrPatch) that uses optical characteristics to effectively reduce conspicuousness while preserving image independence. We also conducted an analysis of the impact of various image features (such as color, texture, noise, and size) on the effectiveness of an attack patch in physical-world deployment. Our experiments show that attack patches exhibit strong redundancy to brightness and are resistant to color transfer and noise. Based on our findings, we propose some additional methods to further reduce the conspicuousness of BrPatch. Our findings also explain the robustness of attack patches observed in physical-world scenarios.
- Synthesizing robust adversarial examples. In International conference on machine learning, pages 284–293, 2018.
- Hilbert-based generative defense for adversarial examples. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 4784–4793, 2019.
- Adversarial patch. arXiv preprint arXiv:1712.09665, 2017.
- Efficient decision-based black-box adversarial attacks on face recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7714–7722, 2019.
- An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020.
- Adversarial camouflage: Hiding physical-world attacks with natural styles. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1000–1008, 2020.
- Robust physical-world attacks on machine learning models. arXiv preprint arXiv:1707.08945, 2(3):4, 2017.
- Robust physical-world attacks on deep learning visual classification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018.
- Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572, 2014.
- Mask r-cnn. In Proceedings of the IEEE international conference on computer vision, pages 2961–2969, 2017.
- Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition, 2016.
- Adversarial examples in the physical world. In Artificial intelligence safety and security, pages 99–112. 2018.
- Characterizing adversarial subspaces using local intrinsic dimensionality. arXiv preprint arXiv:1801.02613, 2018.
- Towards deep learning models resistant to adversarial examples. arXiv preprint arXiv:1706.06083, 2017.
- The limitations of deep learning in adversarial settings. In 2016 IEEE European symposium on security and privacy (EuroS&P), pages 372–387, 2016.
- Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767, 2018.
- Accessorize to a crime: Real and stealthy attacks on state-of-the-art face recognition. In Proceedings of the 2016 acm sigsac conference on computer and communications security, pages 1528–1540, 2016.
- Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199, 2013.
- Residual convolutional ctc networks for automatic speech recognition. arXiv preprint arXiv:1702.07793, 2017.
- On the convergence and robustness of adversarial training. arXiv preprint arXiv:2112.08304, 2021.
- Improving adversarial robustness requires revisiting misclassified examples. In International Conference on Learning Representations, 2020.
- Skip connections matter: On the transferability of adversarial examples generated with resnets. arXiv preprint arXiv:2002.05990, 2020.
- Making an invisibility cloak: Real world adversarial attacks on object detectors. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part IV 16, pages 1–17, 2020.
- Dirichlet latent variable hierarchical recurrent encoder-decoder in dialogue generation. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 1267–1272, 2019.
- Camou: Learning physical vehicle camouflages to adversarially attack detectors in the wild. In International Conference on Learning Representations, 2019.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.