When Optimization Becomes Manipulation: Defending Generative Search against Malicious Generative Engine Optimization
This paper proposes GEO Defender, a two-stage defense aligned with the attack chain that requires no fine-tuning of the target LLM's source use at inference, and demonstrates that GEO Defender reduces the average attack success rate, retains 94.12% of benign-evidence use, preserves answer quality, and generalizes to un...
Hao-Zhang Li, Yang-Guang Shao, Xin-Jie Lin et al.
· 1 citation