ATT&CK® for Adversarial Machine Learning: Tacky or Tasty?

To respond to the growing threat of attacks on machine learning systems, twelve organizations, including Microsoft, MITRE, Bosch, IBM, and NVIDIA, came together to design the first Adversarial ML Threat Matrix fashioned after MITRE ATT&CK framework. Join this session to help refine the framework and brainstorm how it can be used in practice. This session will follow Chatham House Rule to allow for free exchange of information and learning. We look forward to participants actively engaging in the discussion, and remind attendees that no comment attribution or recording of any sort should take place. Pre-Requisites: Attendees need to be familiar with basic ATT&CK framework (e.g: tactic vs. technique). No knowledge of Adversarial ML is required. This is a capacity-controlled session. If added to your schedule and your availability changes, please remove this session from your schedule to allow others to participate.