Alert button
Picture for Lindsey Kuper

Lindsey Kuper

Alert button

Toward Scalable Verification for Safety-Critical Deep Networks

Feb 02, 2018
Lindsey Kuper, Guy Katz, Justin Gottschlich, Kyle Julian, Clark Barrett, Mykel Kochenderfer

Figure 1 for Toward Scalable Verification for Safety-Critical Deep Networks

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.

* Accepted for presentation at SysML 2018 
Viaarxiv icon