Author:
Athavale Anagha,Bartocci Ezio,Christakis Maria,Maffei Matteo,Nickovic Dejan,Weissenbacher Georg
Abstract
AbstractWe present the first automated verification technique for confidence-based 2-safety properties, such as global robustness and global fairness, in deep neural networks (DNNs). Our approach combines self-composition to leverage existing reachability analysis techniques and a novel abstraction of the softmax function, which is amenable to automated verification. We characterize and prove the soundness of our static analysis technique. Furthermore, we implement it on top of Marabou, a safety analysis tool for neural networks, conducting a performance evaluation on several publicly available benchmarks for DNN verification.
Publisher
Springer Nature Switzerland
Reference51 articles.
1. Gurney, K.: An Introduction to Neural Networks. CRC Press, Boca Raton (1997)
2. Goodfellow, I.J., Bengio, Y., Courville, A.C.: Deep Learning. Adaptive Computation and Machine Learning. MIT Press, Cambridge (2016)
3. Amato, F., López, A., Peña-Méndez, E.M., Vaňhara, P., Hampl, A., Havel, J.: Artificial neural networks in medical diagnosis (2013)
4. Rao, Q., Frtunikj, J.: Deep learning for self-driving cars: chances and challenges. In: Proceedings of the 1st International Workshop on Software Engineering for AI in Autonomous Systems, pp. 35–38 (2018)
5. Duan, J.: Financial system modeling using deep neural networks (DNNs) for effective risk assessment and prediction. J. Franklin Inst. 356(8), 4716–4731 (2019)