Joe Gardner from the Cyber Security practice and runner of Bristol Ethical Hackers is giving a talk on hacking ML.
Abstract: Machine learning (ML) has become a topic of importance in the cyber security space over recent years, with numerous products being developed featuring ML algorithms to aid in attack detection. By introducing ML into systems, they become smarter and better at detecting attacks. However, one thing that is often overlooked when deploying ML in security applications is the robustness of the algorithm itself. Frequently, existing algorithms and frameworks are used which were not developed with an adversary in mind. What happens if an attacker doesn’t want to be classified? In this talk I will provide an overview of the current academic space in attacking ML algorithms, and discuss some of the approaches that can be made to make ML more secure in the face of an adversary.