Break the Bot: AI Purple Teaming

​In this free lightning lesson, you will see real attacks against a flawed AI implementation, then watch them get fixed and validated, live.

​🧠 What you will learn:

• ​What the updated OWASP LLM Top 10 means in practice

• ​How prompt injection works, both direct and indirect

• ​Why current prompt injection mitigations often fall short

• ​The break, fix, validate loop that purple teamers use to secure AI systems

​👥 Who this is for:

• ​Penetration testers curious about AI security

• ​Anyone building, deploying, or securing AI or agentic systems

• ​Security fundamentals recommended

​👨‍💻 Instructor:

​Jacob Simmons, Co-Founder, Aphotic Security

​Jacob Simmons is the Co-Founder of Aphotic Security and an OSCP-certified cybersecurity professional and ethical hacker with a BEng in Computer Engineering. He moved into offensive security to help organizations counter evolving digital threats, combining penetration testing and cloud security expertise with hands-on, real-world experience. Jacob has presented research at BSides Cape Town, BSides Johannesburg, and the AISA conference, and recently delivered a webinar on practical AI security, focused on separating real agentic security problems from industry hype. When he is not breaking AI systems, he enjoys finding new ways to hack cloud environments.