Towards Verification of Artificial Neural Networks

By Karsten Scheibler, Leonore Winterer, Ralf Wimmer, B. Becker. 2015

72 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Hadi Salman
2. Huan Zhang
3. Greg Yang
4. Cho-Jui Hsieh
5. Eric Wong
6. Kai Y. Xiao
7. Vincent Tjeng
8. Souradeep Dutta

Citations in the corpus

• Evaluating Robustness of Neural Networks with Mixed Integer Programming (2017, methodology): “When compared to SMT-based approaches, our verifier is two to three orders of magnitude faster than the state-of-the-art verifier, Reluplex, on the task of finding minimum adversarial distortions.”
• A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networks (2019, methodology): “…(1) by typically employing MILP solvers (Cheng et al., 2017; Lomuscio & Maganti, 2017; Dutta et al., 2018; Fischetti & Jo, 2017; Tjeng et al., 2019; Xiao et al., 2019) or Satisfiability Modulo Theories (SMT) solvers (Scheibler et al., 2015; Katz et al., 2017; Carlini et al., 2017; Ehlers, 2017).”
• Output Range Analysis for Deep Feedforward Neural Networks (2018, background): “Recently, there has been a surge of interest in formal verification tools for neural networks [14, 10, 23, 22, 30, 31, 8, 25, 18].”