Thursday
Room 1
15:00 - 16:00
(UTC±00)
Talk (60 min)
Breaking the AI Cage: Prompt Injection Is Inevitable. Impact Is Optional
Prompt injections are inevitable, but impact is optional.
Security
AI Agents
AI Tools and Data
This fast-paced talk focuses on practical exploitation and real-world attack chains in AI-powered web apps. You will learn how attackers build rapport with LLMs, manipulate behavior, and bypass restrictions.
We will demonstrate how seemingly benign vulnerabilities can be chained together to steal and exfiltrate sensitive data through indirect prompt injections, malicious rendering techniques, and abusive tool calls.
Finally, we will break down the reality of AI risk and show exactly how to build the guardrails you need to stop these attacks.-

