Скачать или смотреть Applying DevSecOps Lessons to MLSecOps

As we have seen with AIxCC, AI brings new tools to help with cybersecurity. But developing and operating AI/ML applications introduces new dimensions of risk due to their dynamic behavior, inherent complexity, and often opaque decision-making processes. The transition from Development and Operations (DevOps) to Development, Security, and Operations (DevSecOps) revealed the need for security practices integrated into the Software Development Life Cycle (SDLC) to address critical software security gaps. Machine Learning Operations (MLOps) will now need to go through the same transition into MLSecOps. MLSecOps places a strong emphasis on integrating security practices within the ML development life cycle. It establishes security as a shared responsibility among ML developers, security practitioners, and operations teams. Embracing this methodology enables early identification and mitigation of security risks, facilitating the development of secure and trustworthy ML models.

Speakers:
Christopher Robinson, Chief Security Architect, OpenSSF
Sarah Evans, Security Research Program Lead, Dell Technologies
Eoin Wickens, Director of Threat Intelligence, HiddenLayer
Jeff Diecks, Technical Project Manager, OpenSSF (moderator)