2000 character limit reached
Analyzing Neural Network Robustness Using Graph Curvature
Published 25 Oct 2024 in cs.LG | (2410.19607v2)
Abstract: This paper presents a new look at the neural network (NN) robustness problem, from the point of view of graph theory analysis, specifically graph curvature. Graph curvature (e.g., Ricci curvature) has been used to analyze system dynamics and identify bottlenecks in many domains, including road traffic analysis and internet routing. We define the notion of neural Ricci curvature and use it to identify bottleneck NN edges that are heavily used to ``transport data" to the NN outputs. We provide an evaluation on MNIST that illustrates that such edges indeed occur more frequently for inputs where NNs are less robust. These results will serve as the basis for an alternative method of robust training, by minimizing the number of bottleneck edges.
- A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly et al., “An image is worth 16x16 words: Transformers for image recognition at scale,” arXiv preprint arXiv:2010.11929, 2020.
- R. Ivanov, T. J. Carpenter, J. Weimer, R. Alur, G. J. Pappas, and I. Lee, “Case study: verifying the safety of an autonomous racing car with a neural network controller,” in Proceedings of the 23rd International Conference on Hybrid Systems: Computation and Control, 2020.
- D. Driess, F. Xia, M. S. Sajjadi, C. Lynch, A. Chowdhery, B. Ichter, A. Wahid, J. Tompson, Q. Vuong, T. Yu et al., “Palm-e: An embodied multimodal language model,” arXiv preprint arXiv:2303.03378, 2023.
- C. Szegedy, W. Zaremba, I. Sutskever, J. Bruna, D. Erhan, I. Goodfellow, and R. Fergus, “Intriguing properties of neural networks,” arXiv:1312.6199, 2013.
- B. Recht, R. Roelofs, L. Schmidt, and V. Shankar, “Do imagenet classifiers generalize to imagenet?” in ICML, 2019.
- A. Madry, A. Makelov, L. Schmidt, D. Tsipras, and A. Vladu, “Towards deep learning models resistant to adversarial attacks,” arXiv:1706.06083, 2017.
- J. Cohen, E. Rosenfeld, and Z. Kolter, “Certified adversarial robustness via randomized smoothing,” in international conference on machine learning. PMLR, 2019, pp. 1310–1320.
- E. Wong and Z. Kolter, “Provable defenses against adversarial examples via the convex outer adversarial polytope,” in International conference on machine learning. PMLR, 2018, pp. 5286–5295.
- N. Papernot, P. McDaniel, X. Wu, S. Jha, and A. Swami, “Distillation as a defense to adversarial perturbations against deep neural networks,” in IEEE symposium on security and privacy (SP), 2016, pp. 582–597.
- A. Robey, L. Chamon, G. J. Pappas, H. Hassani, and A. Ribeiro, “Adversarial robustness with semi-infinite constrained learning,” Advances in Neural Information Processing Systems, vol. 34, pp. 6198–6215, 2021.
- “RobustBench: A standardized benchmark for adversarial robustness,” https://robustbench.github.io/.
- Y. Ollivier, “Ricci curvature of Markov chains on metric spaces,” J. Functional Analysis, vol. 256, no. 3, pp. 810–864, 2009.
- Y. Wang, Z. Huang, G. Yin, H. Li, L. Yang, Y. Su, Y. Liu, and X. Shan, “Applying ollivier-ricci curvature to indicate the mismatch of travel demand and supply in urban transit network,” International Journal of Applied Earth Observation and Geoinformation, vol. 106, 2022.
- L. Gao, X. Liu, Y. Liu, P. Wang, M. Deng, Q. Zhu, and H. Li, “Measuring road network topology vulnerability by ricci curvature,” Physica A: Statistical Mechanics and Its Applications, vol. 527, 2019.
- C.-C. Ni, Y.-Y. Lin, J. Gao, X. D. Gu, and E. Saucan, “Ricci curvature of the internet topology,” in 2015 IEEE conference on computer communications (INFOCOM). IEEE, 2015, pp. 2758–2766.
- M. R. Znaidi, J. Sia, S. Ronquist, I. Rajapakse, E. Jonckheere, and P. Bogdan, “A unified approach of detecting phase transition in time-varying complex networks,” Scientific reports, vol. 13, no. 1, 2023.
- H. Li, J. Cao, J. Zhu, Y. Liu, Q. Zhu, and G. Wu, “Curvature graph neural network,” Information Sciences, vol. 592, pp. 50–66, 2022.
- H. Farooq, Y. Chen, T. T. Georgiou, A. Tannenbaum, and C. Lenglet, “Network curvature as a hallmark of brain structural connectivity,” Nature communications, vol. 10, no. 1, p. 4937, 2019.
- J. Sia, E. Jonckheere, and P. Bogdan, “Ollivier-Ricci curvature-based method to community detection in complex networks,” Scientific Reports, vol. 9, no. 1, p. 9800, 12 2019.
- J. Sia, W. Zhang, E. Jonckheere, D. Cook, and P. Bogdan, “Inferring functional communities from partially observed biological networks exploiting geometric topology and side information,” Scientific Reports, vol. 12, no. 1, p. 10883, 2022.
- S. Bochner, “Vector fields and ricci curvature,” 1946.
- C.-C. Ni, Y.-Y. Lin, F. Luo, and J. Gao, “Community detection on networks with ricci flow,” Scientific reports, vol. 9, no. 1, p. 9984, 2019.
- Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based learning applied to document recognition,” Proceedings of the IEEE, vol. 86, no. 11, pp. 2278–2324, 1998.
- F. Brau, G. Rossolini, A. Biondi, and G. Buttazzo, “Robust-by-design classification via unitary-gradient neural networks,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, 2023.
- K. Leino, Z. Wang, and M. Fredrikson, “Globally-robust neural networks,” in Intl. Conf. on Machine Learning, 2021, pp. 6212–6222.
- D. Zou, R. Balan, and M. Singh, “On lipschitz bounds of general convolutional neural networks,” IEEE Transactions on Information Theory, vol. 66, no. 3, pp. 1738–1759, 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.
