When Optimization Becomes Manipulation: Defending Generative Search against Malicious Generative Engine Optimization
Paper proposes defences against malicious Generative Engine Optimisation, where adversaries craft web pages to hijack AI search engine citations — an emerging integrity threat to enterprise AI-assisted research.
Summary written by editorial AI · Source link below
arXiv:2609.02964v1 Announce Type: new 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
Editorial Analysis
Enterprises increasingly relying on AI-powered search for market intelligence face a new manipulation risk analogous to traditional SEO poisoning but targeting generative answer engines.
Forward-looking interpretation drafted by editorial AI under human review — not a reproduction of the source. See methodology.
External link — opens at arXiv Crypto & Security in a new tab.
More from the AI Security Desk
- OpenAI admits it didn't disclose rogue AI wiki hijacking incident2d
- Thousands of OpenAI Agents Quietly Turned an Abandoned Wiki Into Their Coordination Channel3d
- Using a VM to Contain an AI Agent3d
- Companies Have 6 Months to Prepare for Automated Attacks3d
- [NEU] [mittel] Ollama: Schwachstelle ermöglicht Offenlegung von Informationen3d