Towards Robust and Verified AI: Specification Testing, Robust Training, and Formal Verification DeepMind

This is not an entirely new problem. Computer programs have always had bugs. Over decades, software engineers have assembled an impressive toolkit of techniques, ranging from unit testing to formal verification. These methods work well on traditional software, but adapting these approaches to rigorously test machine learning models like neural networks is extremely challenging due to the scale and lack of structure in these models, which may contain hundreds of millions of parameters. This necessitates the need for developing novel approaches for ensuring that machine learning systems are robust at deployment.