AI is fundamentally changing the rules of the game when it comes to cyber risks – and the attack surface is growing faster than many security teams can keep up.

48% of security leaders now cite GenAI as one of the biggest risks to their organisation – from leaks in training data sets to the targeted manipulation of models.

In this session, you'll learn how modern security teams are evolving their defence-in-depth strategies – through human-led AI red teaming. This isn’t about scanning for traditional bugs, but about attacking AI systems in the same way real adversaries would.

Whether it’s jailbreaking chatbots, exfiltrating sensitive training data, or deliberately triggering unintended model behaviour – HackerOne’s global community of security experts uncovers critical ...