Towards proving the adversarial robustness of deep neural networks

Guy Katz*, Clark Barrett, David L. Dill, Kyle Julian, Mykel J. Kochenderfer

*Corresponding author for this work

Research output: Contribution to journalConference articlepeer-review

45 Scopus citations


Autonomous vehicles are highly complex systems, required to function reliably in a wide variety of situations. Manually crafting software controllers for these vehicles is difficult, but there has been some success in using deep neural networks generated usingmachine-learning. However, deep neural networks are opaque to human engineers, rendering their correctness very difficult to provemanually; and existing automated techniques, which were not designed to operate on neural networks, fail to scale to large systems. This paper focuses on proving the adversarial robustness of deep neural networks, i.e. proving that small perturbations to a correctly-classified input to the network cannot cause it to be misclassified. We describe some of our recent and ongoing work on verifying the adversarial robustness of networks, and discuss some of the open questions we have encountered and how they might be addressed.

Original languageAmerican English
Pages (from-to)19-26
Number of pages8
JournalElectronic Proceedings in Theoretical Computer Science, EPTCS
StatePublished - 7 Sep 2017
Externally publishedYes
Event1st Workshop on Formal Verification of Autonomous Vehicles, FVAV 2017 - Turin, Italy
Duration: 19 Sep 2017 → …

Bibliographical note

Funding Information:
Acknowledgements. We thank Neal Suchy from the FAA and Lindsey Kuper from Intel for their valuable comments and support. This work was partially supported by grants from the FAA and Intel.


Dive into the research topics of 'Towards proving the adversarial robustness of deep neural networks'. Together they form a unique fingerprint.

Cite this