paperSeptember 2026Unreviewed

When Optimization Becomes Manipulation: Defending Generative Search against Malicious Generative Engine Optimization

Haozhang Li, Yangguang Shao, Xinjie Lin, Zhong Guan, Mi Zhou, Junzheng Shi

Abstract

This paper focuses on defending generative search engines against malicious Generative Engine Optimization (GEO), which rewrites web documents to match engines' citation preferences and thereby manipulates generated answers. Recent GEO methods have advanced from hand-crafted rewriting to automated and agentic optimization, substantially increasing the visibility of target documents in generated answers. However, defending against such manipulation poses two major challenges: attack documents rem

Cite

@misc{li2026whenb,
  title = {{When Optimization Becomes Manipulation: Defending Generative Search against Malicious Generative Engine Optimization}},
  author = {Haozhang Li and Yangguang Shao and Xinjie Lin and Zhong Guan and Mi Zhou and Junzheng Shi},
  year = {2026},
  month = sep,
  eprint = {2609.02964},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.02964}
}