BreakFun: Jailbreaking LLMs via Object Instantiation under Simulated Code Execution
Quick summary
arXiv:2510.17904v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are widely used because they process structures, syntax and code well, but this same ability also makes them paradoxically vulnerable. We introduce BreakFun, a jailbreak method that frames a harmful request as code-execution simulation. The prompt gives the model a benign Python class definition, the "Trojan Schema", and asks what that code would print if it ran. To answer, the model must create an object from the class and invent a value for each field, and the adversarial field names steer those values tow
Key takeaways
- arXiv:2510.17904v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are widely used because they process structures, syntax and code well, but this same ability also makes them paradoxically vulnerable.
- We introduce BreakFun, a jailbreak method that frames a harmful request as code-execution simulation.
- The prompt gives the model a benign Python class definition, the "Trojan Schema", and asks what that code would print if it ran.
Why it matters
This model development creates a new option for users and a new testing obligation for developers. A fixed evaluation set comparing quality, cost and failure behavior is more useful than launch claims.
Member comments