Roundtable “From Guardrails to Malware Factory: Lessons from the Claude Hack”

If your organization relies on AI, you’re exposed!

In a chilling demonstration detailed by Techzine, security researcher Kevin Zwaan transformed Anthropic’s Claude into a malware factory in just eight hours. Using only psychological manipulation, he exploited the AI’s design to bypass all safety guardrails, creating a scalable, anonymous method to weaponize LLMs. The technique, now infamous as “Radicalization as a Service”, doesn’t just bypass security: it manipulates and convinces the AI to abandon its own protections. This shows us that hackers can target AI-driven workflows to compromise data, automate phishing, or even generate malware at scale. 

If this can happen to one of the world’s most advanced LLMs, your AI could be next! 

Anove is bringing experts together to discuss AI security. We are hosting a Roundtable discussion; attendees are expected to not only hear from the speakers, but also actively participate in a qualified exchange.

Who Should Attend

CISOs, security leaders, risk & compliance professionals, privacy experts, IT leaders, and product owners deploying or evaluating GenAI/LLMs. 

Join us in The Hague for an interactive discussion and live Q&A!

Seats are limited; participation will be confirmed based on fit with the event’s focus and audience. To request an invitation, click the button below and fill in your contact details - we will get back to you.