HarDBench: A Benchmark for Draft-Based Co-Authoring Jailbreak Attacks for Safe Human-LLM Collaborative Writing

Abstract

Large language models (LLMs) are increasingly used as co-authors in collaborative writing, where users begin with rough drafts and rely on LLMs to complete, revise, and refine their content. However, this capability poses a serious safety risk: malicious users could jailbreak the models-filling incomplete drafts with dangerous content-to force them into generating harmful outputs. In this paper, we identify the vulnerability of current LLMs to such draft-based co-authoring jailbreak attacks and

Categories

Framework mappings

Suggested from the entry's categories.

@misc{kim2026hardbench,
  title = {{HarDBench: A Benchmark for Draft-Based Co-Authoring Jailbreak Attacks for Safe Human-LLM Collaborative Writing}},
  author = {Euntae Kim and Soomin Han and Buru Chang},
  year = {2026},
  month = apr,
  eprint = {2604.19274},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.19274}
}