Indirect Prompt Injection: Architectural Testing Approaches for Real World AI/ML Systems
Analyzes indirect Prompt Injection: Architectural Testing Approaches for Real World AI/ML Systems and evaluates key implications for security practitioners.
Summary
No summary yet — watch the video above, or open it on YouTube.
Related talks
Briefings·26 min
Jiashuo Liang · Guancheng Li
Introduces a novel gradient-based prompt-injection technique that can generate universal triggers to manipulate open-source Large Language Model (LLM) outputs.
BSidesSF 2025·35 min
Ahmed Abugharbia
Presenters detail vulnerability discovery and exploitation in GenAI Application Security: Not Just Prompt Injection (Ahmed Abugharbia).
Black Hat·24 min
a Physical Blast Radius
Industry experts analyze emerging threats surrounding Kinetic Prompt Injection: Agent Compromise With a Physical Blast Radius.