Enhancing CT Segmentation Security against Adversarial Attack: Most Activated Filter Approach
Source abstract
Abstract
This study introduces a deep-learning-based framework for detecting adversarial attacks in CT image segmentation within medical imaging. The proposed methodology includes analyzing features from various layers, particularly focusing on the first layer, and utilizing a convolutional layer-based model with specialized training. The framework is engineered to differentiate between tampered adversarial samples and authentic or noise-altered images, focusing on attack methods predominantly utilized in the medical sector. A significant aspect of the approach is employing a random forest algorithm as a binary classifier to detect attacks. This method has shown efficacy in identifying genuine samples and reducing false positives due to Gaussian noise. The contributions of this work include robust attack detection, layer-specific feature analysis, comprehensive evaluations, physician-friendly visualizations, and distinguishing between adversarial attacks and noise. This research enhances the security and reliability of CT image analysis in diagnostics.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Adversarial Robustness in Machine Learning · Anomaly Detection Techniques and Applications · Bacillus and Francisella bacterial research
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Applied Artificial Intelligence, Hanyang University ERICA Campus, 55, Hanyangdaehak-ro, Ansan-si 15588, Gyeonggi-do, Republic of Korea
Funding
Seoul R&BD Program · Institute of Information and communications Technology Planning and Evaluation (IITP) · BK21 FOUR (Fostering Outstanding Universities for Research)
References (29)
Show source-provided references
1. Diagnostic accuracy of deep learning in medical imaging: A systematic review and meta-analysis10.1038/s41746-021-00438-z ↗
2. Systematic review of deep learning image analyses for the diagnosis and monitoring of skin disease10.1038/s41746-023-00914-8 ↗
3. Tang, Y., Yang, D., Li, W., Roth, H.R., Landman, B., Xu, D., Nath, V., and Hatamizadeh, A. (2022, January 19–24). Self-supervised pre-training of swin transformers for 3d medical image analysis. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.10.1109/CVPR52688.2022.02007 ↗
4. nnU-Net: A self-configuring method for deep learning-based biomedical image segmentation10.1038/s41592-020-01008-z ↗
5. Goodfellow, I.J., Shlens, J., and Szegedy, C. (2014). Explaining and harnessing adversarial examples. arXiv.
6. Kurakin, A., Goodfellow, I.J., and Bengio, S. (2018). Artificial Intelligence Safety and Security, Chapman and Hall/CRC.
7. Qi, G., Lijun, G., Song, Y., Ma, K., and Zheng, Y. (May, January 26). Stabilized medical image attacks. Proceedings of the International Conference on Learning Representations, Virtual.
8. Adversarial attacks on medical machine learning10.1126/science.aaw4399 ↗
9. Non-local context encoder: Robust biomedical image segmentation against adversarial attacks
10. Park, H., Bayat, A., Sabokrou, M., Kirschke, J.S., and Menze, B.H. (2020, January 8). Robustification of segmentation models against adversarial perturbations in medical imaging. Proceedings of the International Workshop on PRedictive Intelligence in Medicine, Lima, Peru.10.1007/978-3-030-59354-4_5 ↗
11. Meng, D., and Chen, H. (November, January 30). Magnet: A two-pronged defense against adversarial examples. Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security, Dallas, TX, USA.10.1145/3133956.3134057 ↗
12. Dong, J., Chen, J., Xie, X., Lai, J., and Chen, H. (2023). Adversarial Attack and Defense for Medical Image Analysis: Methods and Applications. arXiv.
13. Muoka, G.W., Yi, D., Ukwuoma, C.C., Mutale, A., Ejiyi, C.J., Mzee, A.K., Gyarteng, E.S., Alqahtani, A., and Al-antari, M.A. (2023). A comprehensive review and analysis of deep learning-based medical image adversarial attack and defense. Mathematics, 11.10.3390/math11204272 ↗
14. Feature visualization10.23915/distill.00007 ↗
15. Ronneberger, O., Fischer, P., and Brox, T. (2015). Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015, Proceedings of the 18th International Conference, Munich, Germany, 5–9 October 2015, Springer. Proceedings, Part III 18.
16. Gonzalez, R.C. (2009). Digital Image Processing, Pearson Education India.10.1117/1.3115362 ↗
17. Landman, B., Xu, Z., Igelsias, J., Styner, M., Langerak, T., and Klein, A. (2015, January 5–9). Miccai multi-atlas labeling beyond the cranial vault–workshop and challenge. Proceedings of the MICCAI Multi-Atlas Labeling Beyond Cranial Vault—Workshop Challenge, Munich, Germany.
18. Jha, D., Smedsrud, P.H., Riegler, M.A., Halvorsen, P., de Lange, T., Johansen, D., and Johansen, H.D. (2020). MultiMedia Modeling, Proceedings of the 26th International Conference, MMM 2020, Daejeon, Republic of Korea, 5–8 January 2020, Springer. Proceedings, Part II 26.
19. Loshchilov, I., and Hutter, F. (May, January 30). Decoupled Weight Decay Regularization. Proceedings of the International Conference on Learning Representations, Vancouver, BC, Canada.
20. Random forests10.1023/A:1010933404324 ↗
21. LeCun, Y., Cortes, C., and Burges, C. (2010). MNIST Handwritten Digit Database, ATT Labs. Available online: http://yann.lecun.com/exdb/mnist.
22. Krizhevsky, A. (2009). Learning Multiple Layers of Features from Tiny Images, University of Toronto. Technical Report.
23. Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., and Antiga, L. (2019, January 8–14). Pytorch: An imperative style, high-performance deep learning library. Proceedings of the Advances in Neural Information Processing Systems, Vancouver, BC, Canada.
24. Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., and Devin, M. (2015). TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. arXiv.
25. Scikit-learn: Machine Learning in Python
26. Chen, T., and Guestrin, C. (2016, January 13–17). Xgboost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.10.1145/2939672.2939785 ↗
27. Moosavi-Dezfooli, S.M., Fawzi, A., and Frossard, P. (July, January 26). Deepfool: A simple and accurate method to fool deep neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.
28. One pixel attack for fooling deep neural networks10.1109/TEVC.2019.2890858 ↗
29. Ozbulak, U., Van Messem, A., and De Neve, W. (2019). Medical Image Computing and Computer Assisted Intervention–MICCAI 2019, Proceedings of the 22nd International Conference, Shenzhen, China, 13–17 October 2019, Springer. Proceedings, Part II 22.