Programme topic
Security & safety
Agents can browse, call tools, mutate systems and act with delegated authority. This collection examines red-teaming, isolation, runtime protection and safer architectures for containing that expanded attack surface.
12 published talks
Talks about security & safety
Ship AI Agents Faster, from Prototype to Production
Sean SpiresSenior Solutions Engineer, Auth0
As AI agents take on more autonomous roles, the identity and access patterns built for humans and APIs no longer hold. This session draws on Auth0’s…
Beyond System Prompts: Securing AI Agents with Fine-Grained Authorization
Daizen IkeharaPrincipal Developer Advocate, Auth0
To make an AI agent useful, we often give it broad access to APIs and data. As systems move from simple retrieval to autonomous action, system-prompt…
How to Count to One Hundred
Hugo O'ConnorR&D Engineer, Anuna Research
Agents don't work well together in chat rooms: put a few in a channel and they talk past each other. Natural language and unrestricted JSON feed an…
Safely releasing AI applications while continuously patching vulnerabilities
Jay YuanStaff Software Engineer, Commonwealth Bank of Australia
AI applications still need regular security patches and dependency updates, but those software changes can also affect the data processing, model…
Autonomous agents need autonomous protection
Adesh GairolaFounder and CEO, raxIT Labs
Autonomous agents need autonomous protection. An agent that acts alone at 3am cannot wait for a quarterly pen test, a consultant's report, or a…
Oops I Hacked It Again: Six Months of Red Teaming Our AI Agents
Jon ShenAI Practice Executive - Strategy and Governance, Suncorp
In March I onboarded our first team member dedicated to AI Red Teaming. That was a month before the announcement of Claude Mythos Preview, and the…
Deliberate Holes Only
Karla BurnettSecurity Engineer, Lorikeet
Making an AI agent vulnerable to exactly one attack is harder than making it completely secure, let alone doing it six different times. In this talk,…
Building a Security Agent: Model choice, Harnesses and Evals
Simon HarloffCTO, Dam Secure
In this presentation, I’ll show how we set out to give developers useful security feedback on every pull request in under three minutes. The benchmark…
Query before mutation: guardrail patterns for agents that touch production infrastructure
Jeffrey AvenMaintainer, StackQL Studios
Giving an AI agent permission to change production infrastructure removes the human pause that made plan-and-apply safe. In this talk, Jeffrey Aven…
Don't Fight Hallucinations. Make Them Impossible
Nadia MakarevichPrincipal Engineer, Heatseeker
The Heatseeker AI chat answers data questions for marketers who make decisions with million-dollar budgets. Wrong answers or hallucinated numbers are…
Assert Chaos
Chris LienertSenior Principal Engineer, Smart AI Connect
Once a product reaches the wilds of production, all sorts of things can go wrong. Carefully logging and monitoring are one thing, but what if we could…
AI Sandboxes: Running Coding Agents Safely in Production-Grade Environments
Shivay LambaLead Machine Learning | Developer Experience Engineer, Qualcomm
The number of cyber attacks and security risks related to Coding Agents has sky rocketed. AI coding agents like Claude Code, Codex CLI, and Gemini CLI…