AI Agents
Security Week
-
We explore the architecture of agentic systems and practical methods for securing them. Using real‑world case studies, we demonstrate the types of threats that exist and how to integrate security into the AI product development lifecycle.
Build AI systems
you can trust
-
Who is the intensive for?
The intensive is designed for developers, AI and Dev(Sec)Ops engineers, tech leads and architects, technical university students, and anyone who wants to understand the risks and know how to design reliable agentic systems
-
What will it cover?
- How autonomous AI agents work and how they differ from LLMs
- Threats that arise when AI agents operate and learn how to protect systems from attacks, data leaks, configuration errors, and other common risks
- Real‑world cases and best practices for designing secure AI product architectures
What the program covers
leads a Yandex Cloud team that makes AI secure and security intelligent
creates technologies and products for secure software development as part of the SourceCraft team
leads an information security engineering team in the Search Portal Security group
ML developer on VK’s computer vision team
FAQ
Still have questions?
we’ll be happy to help
*This material is provided for informational purposes only. We do not encourage or condone any illegal or unethical activity. All techniques and scenarios described are intended solely to help explain security mechanisms and raise awareness