Multi-modal Agentic AI Cybersecurity Threats
The future is undoubtfully autonomous, and the era of Agentic AI is here.
As frontier model capabilities are evolving however, they are doing so much faster than our safeguards – leaving powerful AI-systems exposed to major hacking risks.
In this talk, we’ll dive deep into bleeding edge of security vulnerabilities in multi-modal Agentic AI systems. You’ll understand threat models and get a front-row look at how adversaries can target an agent’s reasoning brain, exploit its memory, and manipulate the tools it uses to interact with the world — across language, vision, audio, and code.
About the Speaker
Ali Leylani is the Chief AI Officer of Echo Alpha, and a seasoned AI security professional with an unhealthy kink for adversarial techniques and exploits.
Logistics
The venue vill be hostad at the modern & esteemed The Park Forskaren.
Event starts at 5:30 and the doors open 15 minutes prior.
Complementary wraps & dricks will be available incl. vegan options.
