Efficient Verification of ReLU-Based Neural Networks via Dependency Analysis

We introduce an efficient method for the verification of ReLU-based feed-forward neural networks. We derive an automated procedure that exploits dependency relations between the ReLU nodes, thereby pruning the search tree that needs to be considered by MILP-based formulations of the verification problem. We augment the resulting algorithm with methods for input domain splitting and symbolic interval propagation. We present Venus, the resulting verification toolkit, and evaluate it on the ACAS collision avoidance networks and models trained on the MNIST and CIFAR-10 datasets. The experimental results obtained indicate considerable gains over the present state-of-the-art tools.

[1]  Mykel J. Kochenderfer,et al.  Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks , 2017, CAV.

[2]  Mykel J. Kochenderfer,et al.  The Marabou Framework for Verification and Analysis of Deep Neural Networks , 2019, CAV.

[3]  Narendra Karmarkar,et al.  A new polynomial-time algorithm for linear programming , 1984, Comb..

[4]  Alessio Lomuscio,et al.  Formal Verification of CNN-based Perception Systems , 2018, ArXiv.

[5]  Pushmeet Kohli,et al.  A Unified View of Piecewise Linear Neural Network Verification , 2017, NeurIPS.

[6]  Dusan M. Stipanovic,et al.  Fast Neural Network Verification via Shadow Prices , 2019, ArXiv.

[7]  Alessio Lomuscio,et al.  Reachability Analysis for Neural Agent-Environment Systems , 2018, KR.

[8]  Chih-Hong Cheng,et al.  Maximum Resilience of Artificial Neural Networks , 2017, ATVA.

[9]  Pushmeet Kohli,et al.  A Dual Approach to Scalable Verification of Deep Networks , 2018, UAI.

[10]  Russ Tedrake,et al.  Evaluating Robustness of Neural Networks with Mixed Integer Programming , 2017, ICLR.

[11]  Mykel J. Kochenderfer,et al.  Algorithms for Verifying Deep Neural Networks , 2019, Found. Trends Optim..

[12]  Aditi Raghunathan,et al.  Semidefinite relaxations for certifying robustness to adversarial examples , 2018, NeurIPS.

[13]  Matteo Fischetti,et al.  Deep neural networks and mixed integer linear optimization , 2018, Constraints.

[14]  Rüdiger Ehlers,et al.  Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks , 2017, ATVA.

[15]  Junfeng Yang,et al.  Efficient Formal Safety Analysis of Neural Networks , 2018, NeurIPS.

[16]  Swarat Chaudhuri,et al.  AI2: Safety and Robustness Certification of Neural Networks with Abstract Interpretation , 2018, 2018 IEEE Symposium on Security and Privacy (SP).

[17]  Manfred Morari,et al.  Safety Verification and Robustness Analysis of Neural Networks via Quadratic Constraints and Semidefinite Programming , 2019, ArXiv.

[18]  Yann LeCun,et al.  The mnist database of handwritten digits , 2005 .

[19]  Cho-Jui Hsieh,et al.  Efficient Neural Network Robustness Certification with General Activation Functions , 2018, NeurIPS.

[20]  Junfeng Yang,et al.  Formal Security Analysis of Neural Networks using Symbolic Intervals , 2018, USENIX Security Symposium.

[21]  Antonio Criminisi,et al.  Measuring Neural Net Robustness with Constraints , 2016, NIPS.

[22]  Mykel J. Kochenderfer,et al.  Policy compression for aircraft collision avoidance systems , 2016, 2016 IEEE/AIAA 35th Digital Avionics Systems Conference (DASC).

[23]  Christian Tjandraatmadja,et al.  Strong mixed-integer programming formulations for trained neural networks , 2018, Mathematical Programming.

[24]  Alessio Lomuscio,et al.  An approach to reachability analysis for feed-forward ReLU neural networks , 2017, ArXiv.