Can LLMs Reason About Brand Ownership? An Empirical Study of Domain Attribution Intelligence

2026-06-18

AI Summary

This study addresses the challenge of accurately determining brand domain ownership by conducting the first systematic evaluation of large language models (LLMs) on this task. The evaluation encompasses three subtasks—domain enumeration, open-ended ownership inference, and binary ownership classification—using Gemini and Claude model families under four experimental settings: in-context learning, web search, WHOIS lookup, and their combinations. Results show that LLMs achieve 82% precision in domain enumeration using only internal knowledge, yet perform poorly in ownership classification, attaining a macro F1-score of merely 0.37 with in-context learning alone. However, incorporating WHOIS data substantially improves performance, boosting the F1-score by up to 0.65 and achieving 99% precision. This work underscores the necessity of external verification for LLMs in brand intelligence applications and provides empirical grounding for their deployment in security-critical contexts.

Abstract

When a new domain resembling a popular brand appears, defenders face a fundamental ambiguity: it may be an attacker-created squatting site for phishing, or it may be a domain the brand itself registered, either defensively, to block attackers, or legitimately, for a new product or service launch. Incorrectly flagging a brand-owned domain as malicious produces a false positive that harms end users and damages the brand's reputation. Resolving this ambiguity requires brand intelligence: the ability to determine, at scale, whether a given domain belongs to a brand. Large language models (LLMs), with their broad knowledge of brand domain relationships, offer a promising zero configuration approach to this problem, but their reliability for brand intelligence tasks remains unknown. We present the first systematic empirical evaluation of LLM brand intelligence across three tasks: domain enumeration (Q1), open ended brand attribution (Q2), and binary ownership classification (Q3). We evaluate four models, Gemini 2.5 Flash, Gemini 3.5 Flash, Claude Sonnet 4.5, and Claude Sonnet 4.6, across four retrieval settings (in context, web search, WHOIS lookup, and combined) on 36 of the most phished brands. Our results reveal a stark dichotomy: models achieve up to 82% precision enumerating brand domains from memory alone, yet fail at ownership verification without external tools, with macro F1 at most 0.37 in ICL mode. WHOIS augmentation lifts Q3 macro F1 by up to 0.65 points, yielding near perfect precision (<= 0.99), dramatically reducing the false positive risk for defenders. We provide concrete recommendations for deploying LLMs in brand protection pipelines.

Problem

• brand ownership
• domain attribution
• phishing detection
• false positive
• brand intelligence

Innovation

• brand intelligence
• domain attribution
• large language models
• WHOIS augmentation
• empirical evaluation