LLM-Guided Prompt Evolution for Password Guessing
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908962796863488 |
|---|---|
| author | Mazin, Vladimir A. Zorin, Mikhail A. Korzh, Dmitrii S. Karimov, Elvir Z. Bolokhov, Dmitrii A. Rogov, Oleg Y. |
| author_facet | Mazin, Vladimir A. Zorin, Mikhail A. Korzh, Dmitrii S. Karimov, Elvir Z. Bolokhov, Dmitrii A. Rogov, Oleg Y. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_12601 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LLM-Guided Prompt Evolution for Password Guessing Mazin, Vladimir A. Zorin, Mikhail A. Korzh, Dmitrii S. Karimov, Elvir Z. Bolokhov, Dmitrii A. Rogov, Oleg Y. Cryptography and Security Artificial Intelligence 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. |
| title | LLM-Guided Prompt Evolution for Password Guessing |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2604.12601 |