paperAugust 2026Unreviewed

Multigranularity Adversarial Attacks on Large Language Models Using Genetic Programming

Wencheng Han, Hao Li, Maoguo Gong, Yu Zhou, Yue Wu, A. Qin, Lining Xing

IEEE Transactions on Evolutionary Computation

Abstract

large language models (LLMs) have demonstrated remarkable capabilities across various natural language processing tasks, but they remain vulnerable to adversarial attacks and pose significant security concerns. Existing attack methods often treat adversarial prompts as flat sequences, neglecting the rich hierarchical structure of natural language, which could limit their effectiveness. Advancing the methodologies for adversarial attacks is crucial for rigorously assessing the security of LLMs an

Framework mappings

MITRE ATLAS

AML.T0043Craft Adversarial Data

Suggested from the entry's categories.

Cite

@article{han2026multigranularity,
  title = {{Multigranularity Adversarial Attacks on Large Language Models Using Genetic Programming}},
  author = {Wencheng Han and Hao Li and Maoguo Gong and Yu Zhou and Yue Wu and A. Qin and Lining Xing},
  year = {2026},
  month = aug,
  journal = {IEEE Transactions on Evolutionary Computation},
  doi = {10.1109/TEVC.2025.3629409},
  url = {https://www.semanticscholar.org/paper/8d3e15cda73e865ccfc8867d11be8352fd8a00d9}
}