LLMmap: Fingerprinting for Large Language Models

Dario Pasquini, Evgenios M. Kornaropoulos, Giuseppe Ateniese

34th USENIX Security Symposium · Day 1

The proliferation of Large Language Models (LLMs) into mainstream applications has introduced a new frontier for cybersecurity research, particularly concerning their inherent vulnerabilities. This paper introduces **LLMmap**, a groundbreaking first-generation active fingerprinting technique designed to identify the specific LLM version powering an application. Much like how network scanners like Nmap identify operating systems, LLMmap sends meticulously crafted queries to an LLM-integrated application and analyzes the responses to deduce the underlying model. This capability is crucial for red teams and security researchers aiming to pinpoint specific attack surfaces and craft targeted exploits.

AI review

This is the Nmap for LLMs, and it's as clean as that sounds. 95% accuracy across 42 model versions with 8 queries, robust against RAG/CoT/system prompts, and the mitigation analysis is brutally honest about why defenders are screwed. Real offensive security research that will change how red teams approach LLM recon.