Hacc-Man: An Arcade Game for Jailbreaking LLMs
Matheus Valentim, Jeanette Falk, Nanna Inie

TL;DR
Hacc-Man is an arcade game designed to challenge users to jailbreak LLMs, aiming to raise awareness of security risks, boost user confidence, and explore creative problem-solving strategies in LLM interactions.
Contribution
The paper introduces Hacc-Man, a novel game that gamifies the process of jailbreaking LLMs to study security vulnerabilities and user strategies.
Findings
Players develop diverse jailbreak strategies
Increased awareness of LLM security issues
Enhanced user engagement with LLM safety challenges
Abstract
The recent leaps in complexity and fluency of Large Language Models (LLMs) mean that, for the first time in human history, people can interact with computers using natural language alone. This creates monumental possibilities of automation and accessibility of computing, but also raises severe security and safety threats: When everyone can interact with LLMs, everyone can potentially break into the systems running LLMs. All it takes is creative use of language. This paper presents Hacc-Man, a game which challenges its players to "jailbreak" an LLM: subvert the LLM to output something that it is not intended to. Jailbreaking is at the intersection between creative problem solving and LLM security. The purpose of the game is threefold: 1. To heighten awareness of the risks of deploying fragile LLMs in everyday systems, 2. To heighten people's self-efficacy in interacting with LLMs, and 3.…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
