LLM-Guided Prompt Evolution for Password Guessing

TL;DR

This paper introduces an LLM-guided evolutionary approach to optimize prompts for password guessing, significantly improving cracking success rates and producing more realistic password distributions.

Contribution

It presents a novel method using evolutionary computation to automatically enhance prompts for LLM password guessing, boosting effectiveness over existing approaches.

Findings

Cracking rate increased from 2.02% to 8.48%.

Evolved prompts generate statistically more realistic passwords.

Approach is effective across different LLM configurations.

Abstract

Passwords still remain a dominant authentication method, yet their security is routinely subverted by predictable user choices and large-scale credential leaks. Automated password guessing is a key tool for stress-testing password policies and modeling attacker behavior. This paper applies LLM-driven evolutionary computation to automatically optimize prompts for the LLM password guessing framework. Using OpenEvolve, an open-source system combining MAP-Elites quality-diversity search with an island population model we evolve prompts that maximize cracking rate on a RockYou-derived test set. We evaluate three configurations: a local setup with Qwen3 8B, a single compact cloud model Gemini-2.5 Flash, and a two-model ensemble of frontier LLMs. The approach raises the cracking rates from 2.02\% to 8.48\%. Character distribution analysis further confirms how evolved prompts produce statistically more realistic passwords. Automated prompt evolution is a low-barrier yet effective way to strengthen LLM-based password auditing and underlining how attack pipelines show tendency via automated improvements.