English

Toward Scalable Verification for Safety-Critical Deep Networks

Artificial Intelligence 2018-02-06 v2 Logic in Computer Science

Abstract

The increasing use of deep neural networks for safety-critical applications, such as autonomous driving and flight control, raises concerns about their safety and reliability. Formal verification can address these concerns by guaranteeing that a deep learning system operates as intended, but the state of the art is limited to small systems. In this work-in-progress report we give an overview of our work on mitigating this difficulty, by pursuing two complementary directions: devising scalable verification techniques, and identifying design choices that result in deep learning systems that are more amenable to verification.

Keywords

Cite

@article{arxiv.1801.05950,
  title  = {Toward Scalable Verification for Safety-Critical Deep Networks},
  author = {Lindsey Kuper and Guy Katz and Justin Gottschlich and Kyle Julian and Clark Barrett and Mykel Kochenderfer},
  journal= {arXiv preprint arXiv:1801.05950},
  year   = {2018}
}

Comments

Accepted for presentation at SysML 2018

R2 v1 2026-06-22T23:48:31.830Z