Efficient Universal Goal Hijacking with Semantics-guided Prompt Organization

Universal goal hijacking is a kind of prompt injection attack that forces LLMs to return a target malicious response for arbitrary normal user prompts. The previous methods achieve high attack performance while being too cumbersome and time-consuming. Also, they have concentrated solely on optimization algorithms, overlooking the crucial role of the prompt. To this end, we propose a method called POUGH that incorporates an efficient optimization algorithm and two semantics-guided prompt organization strategies. Specifically, our method starts with a sampling strategy to select representative prompts from a candidate pool, followed by a ranking strategy that prioritizes them. Given the sequentially ranked prompts, our method employs an iterative optimization algorithm to generate a fixed suffix that can concatenate to arbitrary user prompts for universal goal hijacking. Experiments conducted on four popular LLMs and ten types of target responses verified the effectiveness.

@article{huang2025_2405.14189,
  title={ Efficient Universal Goal Hijacking with Semantics-guided Prompt Organization },
  author={ Yihao Huang and Chong Wang and Xiaojun Jia and Qing Guo and Felix Juefei-Xu and Jian Zhang and Geguang Pu and Yang Liu },
  journal={arXiv preprint arXiv:2405.14189},
  year={ 2025 }
}