Towards Safety Verification of Direct Perception Neural Networks

April 09, 2019 Β· Declared Dead Β· πŸ› Design, Automation and Test in Europe

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Chih-Hong Cheng, Chung-Hao Huang, Thomas Brunner, Vahid Hashemi arXiv ID 1904.04706 Category cs.SE: Software Engineering Cross-listed cs.LG Citations 16 Venue Design, Automation and Test in Europe Last Checked 4 months ago
Abstract
We study the problem of safety verification of direct perception neural networks, where camera images are used as inputs to produce high-level features for autonomous vehicles to make control decisions. Formal verification of direct perception neural networks is extremely challenging, as it is difficult to formulate the specification that requires characterizing input as constraints, while the number of neurons in such a network can reach millions. We approach the specification problem by learning an input property characterizer which carefully extends a direct perception neural network at close-to-output layers, and address the scalability problem by a novel assume-guarantee based verification approach. The presented workflow is used to understand a direct perception neural network (developed by Audi) which computes the next waypoint and orientation for autonomous vehicles to follow.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Software Engineering

Died the same way β€” πŸ‘» Ghosted