With participation from
AI Agent Security Summit brought to you by Zenity Labs
March 31 | The Cinema @ NeueHouse Madison Square | NYC
With participation from
Johann Rehberger demonstrates how prompt injection attacks can compromise agentic systems (think OpenAI’s Operator and Anthropic’s Claude) and have disastrous implications. He highlights critical vulnerabilities in agents that can affect user privacy, system integrity, and the future of AI-powered automation, and cover the various attempts on mitigation strategies and forward-looking guidance.
Ken Huang, research fellow/co-chair of the AI Safety Working Groups at the CSA, discusses how the rise of Agentic AI presents both huge opportunities and unique security challenges. This keynote delves into the critical aspects of securing Agentic AI, focusing on top agentic threats, threat modeling for AI Agents, using data security context, and how to implement Zero Trust for agents.
This expert panel of CISOs and security leaders as they explore the adoption of Agentic AI across the enterprise. They discuss their unique vantage points on the security challenges, strategies for enabling AI Agents, and relevant existing frameworks. Gain insights into overcoming barriers and identifying solutions for securing AI Agents.
Nate Lee, Founder at Cloudsec.ai and Executive in Residence at Scale Venture Partners, gives a Lightning Talk to walk through 5 key questions for evaluating the security of agentic systems. These questions surface operational risks caused by the novel attack surfaces present when systems utilize agentic components behind the scenes.
Allie Howe, Founder at secVendors, presents a multi-agent system, highlighting its vulnerabilities to prompt injection and excessive agency. She showcases these security threats in action and provide practical solutions to mitigate them effectively.
Vivek Vinod Sharma, Lead Security Architect for AI/ML at Microsoft, speaks about the unique security risks that are introduced by RAG systems; including adversarial manipulation, data leakage, and operations disruptions. The talk highlights real-world attack scenarios and discuss practical insights and mitigation strategies.
Béatrice Moissinac, Principal AI Security Engineer at Zendesk, highlights how GenAI heightens the need for both AI and security experts to come together. But given their widely diverging views on technology, risk acceptance, and more, can Security and AI ever see eye to eye? We recommend concrete actions for efficient, and durable integration of AI, Engineering, and Security teams.
This talk, led by Michael Morgenstern of DayBlink Consulting, covers threats to Agentic models and potential mitigation strategies and leverages real-world examples of attacks for illustration. Examples of known attacks include prompt injection (PI) and jailbreak techniques. Michael offers practical advice on how to manage and protect against PI when building new systems, particularly around indirect PI.
As AI agents assume critical roles across healthcare, security frameworks must evolve beyond technical safeguards to address Contextual Explainability; the ability to provide layered, specific rationales for AI decisions. This session, led by Brian M. Green, Chief AI Ethics Officer & Strategist of Health-Vision.AI, positions AI Agent explainability as a security and governance imperative, using healthcare-specific challenges to illustrate broader AI governance trends.
The smartest, most curious minds in AI security found a space to connect, exchange ideas, and push the boundaries of what’s possible. This summit is for builders, defenders, and thinkers shaping the future of AI Agent security.
Deep, engaging discussions on AI Agent security risks, real-world attack surface evolutions, and how to build defenses that actually work.
Meet, debate, collaborate with top experts and rising voices in AI security. Whether they’re well-known or about to be, they’ll be here.
This is not a product pitch-fest. It’s a meet-up for those who are just as fascinated with, and interested in AI Agents as we are.
With AI Agents becoming integral to many workflows, they introduce unprecedented challenges. This summit navigates the uncharted territories of AI Agents with discussions around:
If you work at the intersection of AI Agents and security this content is for you:
From AI Agent governance and compliance to securing AI innovation at scale, this discussion sets the stage for the summit, outlining where AI security is headed and what organizations need to do now to stay ahead.
High impact talks from top AI security minds, expect bold ideas, observed attack pathways, innovative research, insightful takeaways, and expert knowledge you can apply.
Building relationships that will shape the future of AI security and the kinds of discussions that lead to breakthroughs.
View the on-demand content from the AI Agent Security Summit
We’d love to chat with you about how your team can secure and govern AI Agents everywhere.
Book Demo
