Toward Scalable Verification for Safety-Critical Deep Networks
arXiv: Artificial Intelligence, Volume abs/1801.05950, 2018.
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 system...More
Full Text (Upload PDF)
PPT (Upload PPT)