Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces Counter-GEO-Bench, a novel benchmark designed to evaluate defenses against information-distorting generative engine optimization (GEO) that can mislead large language models (LLMs) by synthesizing distorted answers from GEO-optimized documents. The evaluation reveals that existing defenses only marginally reduce attack success rates, highlighting their limitations in addressing the sophisticated nature of GEO misinformation. In contrast, the proposed C-GEO Guard significantly improves defense efficacy, achieving a 47.6% relative reduction in attack success rate while maintaining near-zero utility loss, demonstrating a viable approach to mitigating this emerging threat.
GEO misinformation can slip past conventional safety measures, but a new benchmark shows a lightweight defense can cut attack success rates by nearly half without sacrificing utility.
Generative engine optimization (GEO) enables content producers to increase the visibility of their web pages in generative search engines, but the same techniques can deliver targeted misinformation when adversaries publish ordinary-looking GEO-optimized documents that victim large language models (LLMs) retrieve and synthesize into distorted answers. No existing benchmark evaluates defenses against this threat under controlled conditions. Therefore, we present Counter-GEO-Bench, a defense benchmark that pairs 247 human-verified, quality-gated queries with information-preserving and information-distorting GEO rewrites, and evaluates defenses on attack success rate (ASR), false positive rate, and answer quality across three victim LLMs. Under Counter-GEO-Bench, three off-the-shelf defenses (Granite Guardian, Llama Guard 3, and NeMo Self-Check Fact-Checking) reduce ASR by at most 5.7% relative, while Granite Guardian's reduction is not statistically significant. Safety-taxonomy guardrails target policy violations, while GEO misinformation passes through them as fluent informational content. To this end, a lightweight benchmark baseline, C-GEO Guard, is proposed, reducing ASR by 47.6% relative with near-zero utility loss, which proves threat tractable.