Persona Attack: Incremental Memory Injection Jailbreak Attack against Large Language Models

Abstract

As Large Language Models evolve for user convenience, vulnerability to jailbreak attacks continues to be reported despite ongoing efforts in safety training. Traditional jailbreak techniques typically focus on a single prompt injection, neglecting the models' ability to remember the flow of conversation and the user's instructions. In this paper, we propose Persona Attack, a memory injection based jailbreak method that manipulates the model's context window through a step by step approach. Exper

Categories

Framework mappings

Suggested from the entry's categories.

@misc{park2026persona,
  title = {{Persona Attack: Incremental Memory Injection Jailbreak Attack against Large Language Models}},
  author = {Junyoung Park and Seongyong Ju and Sunghwan Park and Jaewoo Lee},
  year = {2026},
  month = may,
  eprint = {2606.00150},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.00150}
}