Class Retrieval of Detected Adversarial Attacks
Source abstract
Abstract
Adversarial attack is a genuine threat compromising the safety of many intelligent systems curbing the standardization of using neural networks in security-critical applications. Since the emergence of adversarial attacks, the research community has worked relentlessly to avert the malicious damage of these attacks. Here, we present a new, additional and required element to ameliorate adversarial attacks: the recovery of the original class after a detected attack. Recovering the original class of an adversarial sample without taking any precautions is an uncharted concept which we would like to introduce with our novel class retrieval algorithm. As case studies, we demonstrate the validity of our approach on MNIST, CIFAR10 and ImageNet datasets where recovery rates were 72%, 65% and 65%, respectively.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Adversarial Robustness in Machine Learning · Anomaly Detection Techniques and Applications · Domain Adaptation and Few-Shot Learning
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Faculty of Information Technology and Bionics, Peter Pazmany Catholic University, Práter u. 50/A, 1083 Budapest, Hungary
References (33)
Show source-provided references
1. Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5–9). U-net: Convolutional networks for biomedical image segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany.10.1007/978-3-319-24574-4_28 ↗
2. Ros, G., Sellart, L., Materzynska, J., Vazquez, D., and Lopez, A.M. (2016, January 27–30). The synthia dataset: A large collection of synthetic images for semantic segmentation of urban scenes. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.352 ↗
3. Ni, J., Chen, Y., Zhu, J., Ali, D., and Weidong, C. (2020). A Survey on Theories and Applications for Self-Driving Cars Based on Deep Learning Methods. Appl. Sci., 10.10.3390/app10082749 ↗
4. Papernot, N., McDaniel, P.D., Sinha, A., and Wellman, M.P. (2016). Towards the Science of Security and Privacy in Machine Learning. arXiv.
5. Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., and Fergus, R. (2013). Intriguing properties of neural networks. arXiv.
6. Gilmer, J., Metz, L., Faghri, F., Schoenholz, S.S., Raghu, M., Wattenberg, M., and Goodfellow, I. (2018). Adversarial Spheres. arXiv.
7. Goodfellow, I.J., Shlens, J., and Szegedy, C. (2014). Explaining and Harnessing Adversarial Examples. arXiv.
8. Moosavi-Dezfooli, S., Fawzi, A., Fawzi, O., and Frossard, P. (2016). Universal adversarial perturbations. arXiv.10.1109/CVPR.2017.17 ↗
9. Athalye, A., Engstrom, L., Ilyas, A., and Kwok, K. (2017). Synthesizing Robust Adversarial Examples. arXiv.
10. Sankaranarayanan, S., Jain, A., Chellappa, R., and Lim, S.N. (2018). Regularizing deep networks using efficient layerwise adversarial training. arXiv.10.1609/aaai.v32i1.11688 ↗
11. Ross, A.S., and Doshi-Velez, F. (2017). Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients. arXiv.10.1609/aaai.v32i1.11504 ↗
12. Lu, J., Issaranon, T., and Forsyth, D. (2017). SafetyNet: Detecting and Rejecting Adversarial Examples Robustly. arXiv.10.1109/ICCV.2017.56 ↗
13. Akhtar, N., and Mian, A. (2018). Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey. arXiv.10.1109/ACCESS.2018.2807385 ↗
14. Rozsa, A., Rudd, E.M., and Boult, T.E. (2016, January 27–30). Adversarial diversity and hard positive generation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Las Vegas, NV, USA.10.1109/CVPRW.2016.58 ↗
15. Li, B., Wang, Y., Singh, A., and Vorobeychik, Y. (2016). Data Poisoning Attacks on Factorization-Based Collaborative Filtering. arXiv.
16. Fredrikson, M., Jha, S., and Ristenpart, T. (2015, January 12–16). Model inversion attacks that exploit confidence information and basic countermeasures. Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security, Denver, CO, USA.10.1145/2810103.2813677 ↗
17. Dong, Y., Liao, F., Pang, T., Su, H., Zhu, J., Hu, X., and Li, J. (2018, January 18–23). Boosting adversarial attacks with momentum. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00957 ↗
18. Moosavi-Dezfooli, S.M., Fawzi, A., and Frossard, P. (2016). DeepFool: A simple and accurate method to fool deep neural networks. arXiv.10.1109/CVPR.2016.282 ↗
19. Croce, F., and Hein, M. (2020). Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks. arXiv.
20. Zhang, H., Yu, Y., Jiao, J., Xing, E.P., Ghaoui, L.E., and Jordan, M.I. (2019). Theoretically Principled Trade-off between Robustness and Accuracy. arXiv.
21. Chakraborty, A., Alam, M., Dey, V., Chattopadhyay, A., and Mukhopadhyay, D. (2018). Adversarial Attacks and Defences: A Survey. arXiv.
22. Dziugaite, G.K., Ghahramani, Z., and Roy, D.M. (2016). A study of the effect of JPG compression on adversarial images. arXiv.
23. Luo, Y., Boix, X., Roig, G., Poggio, T., and Zhao, Q. (2016). Foveation-based Mechanisms Alleviate Adversarial Examples. arXiv.
24. Gao, J., Wang, B., Lin, Z., Xu, W., and Qi, Y. (2017). DeepCloak: Masking Deep Neural Network Models for Robustness Against Adversarial Samples. arXiv.
25. Li, X., and Li, F. (2017). Adversarial Examples Detection in Deep Networks with Convolutional Filter Statistics. arXiv.10.1109/ICCV.2017.615 ↗
26. Meng, D., and Chen, H. (2017). MagNet: A Two-Pronged Defense against Adversarial Examples. arXiv.10.1145/3133956.3134057 ↗
27. Detecting Adversarial Image Examples in Deep Neural Networks with Adaptive Noise Reduction10.1109/TDSC.2018.2874243 ↗
28. Carlini, N., and Wagner, D. (2017). Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods. arXiv.10.1145/3128572.3140444 ↗
29. Rozsa, A., Gunther, M., and Boult, T.E. (2018). Towards Robust Deep Neural Networks with BANG. arXiv.10.1109/WACV.2018.00093 ↗
30. Moosavi-Dezfooli, S.M., Fawzi, A., Fawzi, O., Frossard, P., and Soatto, S. (2017). Analysis of universal adversarial perturbations. arXiv.10.1109/CVPR.2017.17 ↗
31. Tramer, F., Kurakin, A., Papernot, N., Goodfellow, I., Boneh, D., and McDaniel, P. (2020). Ensemble Adversarial Training: Attacks and Defenses. arXiv.
32. Madry, A., Makelov, A., Schmidt, L., Tsipras, D., and Vladu, A. (2017). Towards Deep Learning Models Resistant to Adversarial Attacks. arXiv.
33. Kim, H. (2020). Torchattacks: A Pytorch Repository for Adversarial Attacks. arXiv.