Full-day multi-track event brings together researchers, practitioners and security leaders to address emerging threats, vulnerabilities and defense strategies for AI agents

SAN FRANCISCO: #AIAgentSecuritySummit--Zenity, the leading end-to-end security and governance platform for AI agents, today announced the agenda for the upcoming AI Agent Security Summit, taking place May 27, 2026, in San Francisco, bringing together security researchers, practitioners and enterprise leaders to explore the evolving risks and defense strategies associated with AI agents.

Following the launch of the inaugural AI Agent Security Summit series in New York City and San Francisco in 2025, the program is expanding globally in 2026 with additional events planned globally including New York and Asia. Each summit will feature local speakers, new research and technical discussions highlighting emerging vulnerabilities and attack pathways in AI agents.

As AI agent adoption accelerates across enterprise environments, the pace of innovation and risk is evolving rapidly, with new vulnerabilities, attack techniques and defensive approaches emerging in real time. The summit will highlight the latest research, real-world incidents and practitioner insights shaping how organizations are securing agentic systems today.

The San Francisco Summit will feature a full-day, multi-track program with keynotes, sessions, panels and lightning talks. This is a community-focused event where discussions will not include product or vendor talks. Attendees can choose from a range of sessions, followed by a networking happy hour.

The summit covers key challenges surrounding AI agent security, including:

• Real-world attack scenarios targeting AI agents and automated workflows

• Prompt injection, memory poisoning and tool manipulation in agent-based systems

• Runtime defense strategies focused on behavior monitoring and intent validation

• New research and case studies from enterprise security teams and independent researchers

Featured speakers from leading organizations across technology, security and research include:

• Vivek Vinod Sharma, Lead AI Security Architect, Microsoft

• Aron Eidelman, Senior Developer Relations Engineer, AI Security, Google

• Ashay Raut, Principal Engineer, Amazon

• Aditya Dubey, Software Engineer, Lyft

• Travis McPeak, Security Lead, Cursor

• Ben Sadeghipour (Nahamsec), Hacker and CEO, HackingHub

• Allie Howe, Founder, Insecure Agents

• Jim Reavis, CEO, Cloud Security Alliance

• Michael Bargury, Co-Founder and CTO, Zenity (keynote)

The program reflects growing industry focus on securing AI agents as they move from experimental systems to operational components within enterprise environments.

“AI agents are rapidly becoming embedded across crown jewel enterprise applications, where they are making decisions, interacting with systems and executing meaningful actions at scale,” said Michael Bargury, co-founder and CTO of Zenity. “AI adoption has become a modern gold rush, with organizations racing to deploy agents faster than they understand them. But AI systems behave in unpredictable and often non-deterministic ways, creating security risks traditional controls were never designed to handle. As organizations adopt these systems more broadly, the security community needs a dedicated forum to share research, understand emerging threats, and develop practical approaches for defending this new layer of enterprise infrastructure.”

Event Details

• Date: May 27, 2026

• Location: San Francisco, CA

• Info and registration link here

About Zenity

Zenity is the first security and governance platform purpose built for AI agents spanning SaaS, home grown platforms (Cloud) and end user devices (Endpoint). Trusted by Fortune 500 enterprises, Zenity helps security teams confidently adopt AI by delivering defense in depth with full lifecycle coverage, from agent discovery and posture management to real time detection, inline prevention and response. With an agent centric approach that prioritizes how agents behave, what they access and which tools they invoke, Zenity eliminates blind spots and enforces consistent policy and controls across environments so organizations can innovate with AI without compromising security. Learn more at www.zenity.io.

Fonte: Business Wire