September 2025 Kick-off AI Security Guardians Meetup

Kick-off AI Security Guardians Dutch Chapter Meetup

18:00 Walk-in with drinks and food
18:30 SESSION 1 Introduction and inaugural presentation on the research publication "Tree of Attacks - Jailbreaking Black Box LLMs with Algorithmic red teaming". By Amin Karbasi - Senior Director Foundation AI.
19:00 Break and get to know each other
19:15 SESSION 2 Securing the Future: Decentralized Agent-to-Agent Communication. By Raahul Dutta - Founder Pebbing.ai
20:00 Investigate topics that we would like to talk about
20:30 closing

Location: Haarlebergweg 17, Amsterdam

"Tree of Attacks - Jailbreaking Black Box LLMs with Algorithmic red teaming".
While Large Language Models (LLMs) display versatile functionality, they continue to generate harmful, biased, and toxic content, as demonstrated by the prevalence of human-designed jailbreaks. In this work, we present Tree of Attacks with Pruning (TAP), an automated method for generating jailbreaks that only requires black-box access to the target LLM. TAP utilizes an attacker LLM to iteratively refine candidate (attack) prompts until one of the refined prompts jailbreaks the target. In addition, before sending prompts to the target, TAP assesses them and prunes the ones unlikely to result in jailbreaks, reducing the number of queries sent to the target LLM. In empirical evaluations, we observe that TAP generates prompts that jailbreak state-of-the-art LLMs (including GPT4-Turbo and GPT4o) for more than 80% of the prompts. This significantly improves upon the previous state-of-the-art black-box methods for generating jailbreaks while using a smaller number of queries than them. Furthermore, TAP is also capable of jailbreaking LLMs protected by state-of-the-art guardrails, e.g., LlamaGuard.