Abstract
AbstractAlthough state-of-the-art deep neural network models are known to be robust to random perturbations, it was verified that these architectures are indeed quite vulnerable to deliberately crafted perturbations, albeit being quasi-imperceptible. These vulnerabilities make it challenging to deploy deep neural network models in the areas where security is a critical concern. In recent years, many research studies have been conducted to develop new attack methods and come up with new defense techniques that enable more robust and reliable models. In this study, we use the quantified epistemic uncertainty obtained from the model’s final probability outputs, along with the model’s own loss function, to generate more effective adversarial samples. And we propose a novel defense approach against attacks like Deepfool which result in adversarial samples located near the model’s decision boundary. We have verified the effectiveness of our attack method on MNIST (Digit), MNIST (Fashion) and CIFAR-10 datasets. In our experiments, we showed that our proposed uncertainty-based reversal method achieved a worst case success rate of around 95% without compromising clean accuracy.
Publisher
Springer Science and Business Media LLC
Subject
General Earth and Planetary Sciences,General Environmental Science
Reference66 articles.
1. He K, Zhang X, Ren S, Sun J (2015) Deep residual learning for image recognition. arXiv:1512.03385
2. Goodfellow IJ, Bulatov Y, Ibarz J, Arnoud S, Shet V (2014) Multi-digit number recognition from street view imagery using deep convolutional neural networks. arXiv:1312.6082
3. Chouard T (2016) The go files: Ai computer wraps up 4-1 victory against human champion. Nature. https://doi.org/10.1038/nature.2016.19575
4. Shen L, Margolies LR, Rothstein JH, Fluder E, McBride R, Sieh W (2019) Deep learning to improve breast cancer detection on screening mammography. Sci Rep 9(1):12495. https://doi.org/10.1038/s41598-019-48995-4
5. Causey JL, Zhang J, Ma S, Jiang B, Qualls JA, Politte DG, Prior F, Zhang S, Huang X (2018) Highly accurate model for prediction of lung nodule malignancy with ct scans. Sci Rep 8(1):9286. https://doi.org/10.1038/s41598-018-27569-w
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. TENET: a new hybrid network architecture for adversarial defense;International Journal of Information Security;2023-03-17
2. A rubric for human-like agents and NeuroAI;Philosophical Transactions of the Royal Society B: Biological Sciences;2022-12-13
3. Unreasonable Effectiveness of Last Hidden Layer Activations for Adversarial Robustness;2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC);2022-06