When Emotion Becomes Trigger: Emotion-style dynamic Backdoor Attack Parasitising Large Language Models

Ziyu Liu, Tao Li, Tianjie Ni, Xiaolong Lan, Wengang Ma, Tao Yang, Guohua Wang, Junjiang He

Abstract

Backdoor vulnerabilities widely exist in the fine-tuning of large language models(LLMs). Most backdoor poisoning methods operate mainly at the token level and lack deeper semantic manipulation, which limits stealthiness. In addition, Prior attacks rely on a single fixed trigger to induce harmful outputs. Such static triggers are easy to detect, and clean fine-tuning can weaken the trigger-target association. Through causal validation, we observe that emotion is not directly linked to individual

Categories

Cite This Resource

@article{llmsec202600068,
  title = {When Emotion Becomes Trigger: Emotion-style dynamic Backdoor Attack Parasitising Large Language Models},
  author = {Ziyu Liu and Tao Li and Tianjie Ni and Xiaolong Lan and Wengang Ma and Tao Yang and Guohua Wang and Junjiang He},
  year = {2026},
  url = {https://arxiv.org/abs/2605.11612},
}