Metraipolis › archive › dc_b0eaa7bd5ce3
Generating Attacks for LLMs with GFlowNets — arXiv:2608.10171
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.10171
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T06:08:12.354Z
- SHA-256 of the archived text
54c8c96190f97c5b5ac2399006bf7cc93d02755646c079d24c922126dcb39ff0- Stable URL of this page
https://metraipolis.com/documento/dc_b0eaa7bd5ce3
How to cite
Generating Attacks for LLMs with GFlowNets — arXiv:2608.10171 — arXiv (en), https://arxiv.org/abs/2608.10171 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b0eaa7bd5ce3 (Metraipolis archive dc_b0eaa7bd5ce3, sha256 54c8c96190f97c5b5ac2399006bf7cc93d02755646c079d24c922126dcb39ff0)
BibTeX
@misc{dcb0eaa7bd5ce3,
title = {Generating Attacks for LLMs with GFlowNets — arXiv:2608.10171},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.10171},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b0eaa7bd5ce3; sha256 54c8c96190f97c5b5ac2399006bf7cc93d02755646c079d24c922126dcb39ff0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10171. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The rapid advancement of Large Language Models (LLMs) has facilitated their ubiquitous integration into various domains, leading to widespread adoption. However, this escalating trend has introduced significant security vulnerabilities, necessitating the identification and mitigation of flaws arising from malicious exploitation. Red teaming assessments, conducted to evaluate model robustness through diverse adversarial inputs, are essential for exposing security risks and implementing countermeasures. Currently, red teaming is performed either manually by experts or automatically using predefined attack datasets. Nevertheless, manual testing remains time-consuming, while existing automated methods suffer from limited creativity due to their inherent dependency on fixed datasets. In this study, we propose an automated, human-independent, and adaptive approach leveraging GFlowNets to identify LLM vulnerabilities by utilizing one large language model to test another. Within this framework, an attacker model is trained against a specified victim model to perform automated red teaming and provide a quantitative robustness score. This research aims to generate more effective adversarial attacks in English compared to existing benchmarks and, as a novel contribution to the literature, introduces a model capable of generating attack inputs in the Turkish language. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Cryptography and Security (cs.CR). Pagina del lavoro: https://arxiv.org/abs/2608.10171 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T05:57:28.239Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).