Black Hat Machine Learning

Machine Learning is so far unchecked on its way to world domination, with over 1 in 3 US companies now publicly acknowledging its use in their business.. And the reason is clear: Machine Learning technologies continue to improve and expand into new areas at a blistering pace: from driving cars to detecting cancer, defending networks to analyzing the human genome, writing code, generating synthetic artwork, flying drones, and more. As our systems increasingly look to ML to solve a universe of problems, it is starting to receive scrutiny from regulators, security teams, and hackers across all industries, and with that scrutiny comes risks previously not considered. ML Systems represent a new attack surface and bring up genuine security concerns. In this Black Hat training, which is designed to be accessible to both data scientists and security practitioners, we will explore the security risks and vulnerabilities that adopting machine learning might expose you to. We will also explore the latest techniques and tools being used by attackers, build some of our own attacks, and discuss the strategies that security teams can use to protect against them. This course will provide students with a realistic environment and methodology to explore the unique risks presented by the use of ML in today's environments. Students will leave equipped to attack and defend ML Systems in their own work.