ML Conference is the go-to event for Machine Learning enthusiasts, the world’s leading machine learning experts and innovators as they share their ideas and experience.
The founder of Adversa AI Alex Polyakov delivered a presentation dedicated to Threat Modeling for machine learning at the ML Conference Munich 2022 on June 28, 2022. The topic is actively discussed as there is no 100% relevant protection of all AI-based systems in the light of ever-increasing attacks. That’s why defining threats and threat modeling are the first primary step to security.
Alex demonstrated:
- how to deal with the security assessment of ML algorithms;
- how to define a threat model;
- what metrics to choose;
- what approaches to protection can be applied and where;
- how to achieve maximum protection with a reasonable investment of resources.