Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
194 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Localized adversarial artifacts for compressed sensing MRI (2206.05289v2)

Published 10 Jun 2022 in eess.IV, cs.CV, and cs.LG

Abstract: As interest in deep neural networks (DNNs) for image reconstruction tasks grows, their reliability has been called into question (Antun et al., 2020; Gottschling et al., 2020). However, recent work has shown that, compared to total variation (TV) minimization, when appropriately regularized, DNNs show similar robustness to adversarial noise in terms of $\ell2$-reconstruction error (Genzel et al., 2022). We consider a different notion of robustness, using the $\ell\infty$-norm, and argue that localized reconstruction artifacts are a more relevant defect than the $\ell2$-error. We create adversarial perturbations to undersampled magnetic resonance imaging measurements (in the frequency domain) which induce severe localized artifacts in the TV-regularized reconstruction. Notably, the same attack method is not as effective against DNN based reconstruction. Finally, we show that this phenomenon is inherent to reconstruction methods for which exact recovery can be guaranteed, as with compressed sensing reconstructions with $\ell1$- or TV-minimization.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (25)
  1. ADef: an iterative algorithm to construct adversarial deformations. In Proceedings of the International Conference on Learning Representations (ICLR 2019), 2019.
  2. On instabilities of deep learning in image reconstruction and the potential costs of AI. Proceedings of the National Academy of Sciences, 117(48):30088–30095, 2020.
  3. Solving inverse problems using data-driven models. Acta Numerica, 28:1–174, 2019.
  4. Evasion attacks against machine learning at test time. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pages 387–402, New York, 2013. Springer.
  5. Distributed optimization and statistical learning via the alternating direction method of multipliers. Foundations and Trends in Machine learning, 3(1):1–122, 2011.
  6. E. J. Candès and C. Fernandez-Granda. Towards a mathematical theory of super-resolution. Communications on pure and applied Mathematics, 67(6):906–956, 2014.
  7. E. J. Candès and Y. Plan. A probabilistic and RIPless theory of compressed sensing. IEEE transactions on information theory, 57(11):7235–7254, 2011.
  8. Robust uncertainty principles: Exact signal reconstruction from highly incomplete frequency information. IEEE Transactions on information theory, 52(2):489–509, 2006.
  9. AI-based reconstruction for fast MRI—a systematic review and meta-analysis. Proceedings of the IEEE, 110(2):224–245, 2022.
  10. The difficulty of computing stable and accurate neural networks: On the barriers of deep learning and Smale’s 18th problem. Proceedings of the National Academy of Sciences, 119(12):e2107151119, 2022.
  11. Y. De Castro and F. Gamboa. Exact reconstruction using Beurling minimal extrapolation. Journal of Mathematical Analysis and applications, 395(1):336–354, 2012.
  12. S. Foucart and H. Rauhut. A Mathematical Introduction to Compressive Sensing. Springer New York, 2013.
  13. Solving inverse problems with deep neural networks - robustness included. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(1):1119–1134, 2022. doi: 10.1109/TPAMI.2022.3148324.
  14. Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572, 2014.
  15. The troublesome kernel: why deep learning for inverse problems is typically unstable. arXiv preprint arXiv:2001.01258, 2020.
  16. The one hundred layers Tiramisu: Fully convolutional densenets for semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pages 11–19, 2017.
  17. Compressed Sensing MRI. IEEE Signal Processing Magazine, 25(2):72–82, 2008. doi: 10.1109/MSP.2007.914728.
  18. Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083, 2017.
  19. Convolutional neural networks for inverse problems in imaging: A review. IEEE Signal Processing Magazine, 34(6):85–95, 2017. doi: 10.1109/msp.2017.2739299. URL https://doi.org/10.1109%2Fmsp.2017.2739299.
  20. Deep learning techniques for inverse problems in imaging. IEEE Journal on Selected Areas in Information Theory, 1(1):39–56, 2020.
  21. C. Poon. On the role of total variation in compressed sensing. SIAM Journal on Imaging Sciences, 8(1):682–720, 2015.
  22. Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199, 2013.
  23. Accelerating magnetic resonance imaging via deep learning. In Proceedings of the 2016 IEEE 13th International Symposium on Biomedical Imaging, pages 514–517, 2016.
  24. Deep ADMM-Net for Compressive Sensing MRI. In Advances in Neural Information Processing Systems, volume 29, 2016.
  25. Image reconstruction by domain-transform manifold learning. Nature, 555(7697):487–492, 2018.
Citations (4)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now