Work-In-Progress: Testing Autonomous Cyber-Physical Systems Using Fuzzing Features From Convolutional Neural Networks
Abstract
Autonomous cyber-physical systems rely on modern machine learning methods such as deep neural networks to control their interactions with the physical world. Testing of such intelligent cyberphysical systems is a challenge due to the huge state space associated with high-resolution visual sensory inputs. We demonstrate how fuzzing the input using patterns obtained from the convolutional flters of an unrelated convolutional neural network can be used to test computer vision algorithms implemented in intelligent cyber-physical systems. Our method discovers interesting counterexamples to a pedestrian detection algorithm implemented in the popular OpenCV library. Our approach also unearths counterexamples to the correct behavior of an autonomous car similar to NVIDIA's end-to-end self-driving deep neural net running on the Udacity open-source simulator.
Publication Date
10-15-2017
Publication Title
Proceedings of the 13th ACM International Conference on Embedded Software 2017 Companion, EMSOFT 2017
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1145/3125503.3125568
Copyright Status
Unknown
Socpus ID
85034850699 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85034850699
STARS Citation
Raj, Sunny; Jha, Sumit Kumar; Ramanathan, Arvind; and Pullum, Laura L., "Work-In-Progress: Testing Autonomous Cyber-Physical Systems Using Fuzzing Features From Convolutional Neural Networks" (2017). Scopus Export 2015-2019. 6629.
https://stars.library.ucf.edu/scopus2015/6629