Webinar Today: Breaking AI – Inside the Art of LLM Pen Testing

SecurityWeek is running a live webinar titled Webinar Today: Breaking AI – Inside the Art of LLM Pen Testing, which promises a new model for AI pen testing grounded in social engineering, behavioural manipulation and therapeutic dialogue. The session, led with SecurityWeek and Bishop Fox, is scheduled for Thursday 11 September 2025 at 2PM ET, with registration available via the event page.

It argues that effective LLM security testing focuses on persuasion rather than traditional payloads, drawing on hands-on research and real-world client engagements. Attendees will explore Adversarial Prompt Exploitation (APE), a methodology targeting trust boundaries and decision pathways through psychological levers such as emotional preloading, narrative control and language nesting, and will see real-world case studies.

The programme also covers how to communicate findings to executive and technical leadership and offers frameworks for simulating threats to LLM-based systems, as described by SecurityWeek News.