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

ArXi:2604.19274v1 Announce Type: new 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