First white-box testing model finds thousands of errors in self-driving cars

Researchers from Lehigh University and Columbia University shine a light into the black box of deep learning systems with DeepXplore, the first automated white-box testing of such systems. Evaluating DeepXplore on real-world datasets, the researchers were able to expose thousands of unique incorrect corner-case behaviors. They will present their findings at the 2017 biennial ACM Symposium on Operating Systems Principles (SOSP) conference in Shanghai, China on October 29th in Session I: Bug Hunting.
Go to Source