paperAugust 2026Unreviewed

Generating Attacks for LLMs with GFlowNets

Berkay Ozcam, Irem Onen, Mehmet Fatih Amasyali, Emin Islam Tatli

Abstract

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 countermea

Framework mappings

NIST AI Risk Management Framework

MEASUREMeasure

Suggested from the entry's categories.

Cite

@misc{ozcam2026generating,
  title = {{Generating Attacks for LLMs with GFlowNets}},
  author = {Berkay Ozcam and Irem Onen and Mehmet Fatih Amasyali and Emin Islam Tatli},
  year = {2026},
  month = aug,
  eprint = {2608.10171},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.10171}
}