# Preprint proposes defense against manipulated generative-search citations

_Friday, September 4, 2026 at 12:00 AM EDT · AI, Security, Science · Latest · Tier 2 — Notable_

A new arXiv paper describes GEO Defender, a two-stage defense for generative-search systems facing documents rewritten to influence citation preferences. The authors say its reranker demotes manipulated documents while a training-free generation layer guides source use without fine-tuning the target model. In experiments across seven attacks and five closed- and open-source LLMs, the paper reports average attack success falling from 50.32% to 6.20% while retaining 94.12% of benign-evidence use. These are preprint results.

## Sources

- [cs.AI updates on arXiv.org](https://arxiv.org/abs/2609.02964)

---
Canonical: https://techandbusiness.org/newswire/YrNiGbPGZH2KNQNlwlw_Tw
Retrieved: 2026-09-05T02:44:06.266Z
Publisher: Tech & Business (techandbusiness.org)