Gradient-Based Model Fingerprinting for LLM Similarity Detection and Family Classification

--As Large Language Models (LLMs) become integral software components in modern applications, unauthorized model derivations through fine-tuning, merging, and redistribution have emerged as critical software engineering challenges. Unlike traditional software where clone detection and license compliance are well-established, the LLM ecosystem lacks effective mechanisms to detect model lineage and enforce licensing agreements. This gap is particularly problematic when open-source model creators, such as Meta's LLaMA, require derivative works to maintain naming conventions for attribution, yet no technical means exist to verify compliance. These fingerprints enable two complementary capabilities: direct pairwise similarity assessment between arbitrary models through distance computation, and systematic family classification of unknown models via the K-Means clustering algorithm with domain-informed centroid initialization using known base models. Experimental evaluation on 58 models comprising 8 base models and 50 derivatives across five model families (Llama, Qwen, Gemma, Phi, Mistral) demonstrates 94% classification accuracy under our centroid-initialized K-Means clustering. Our work establishes a new paradigm for model similarity detection, bridging traditional software engineering practices with modern LLM distribution and compliance challenges. The proliferation of Large Language Models (LLMs) has fundamentally transformed how we conceptualize and deploy AI-powered software systems. With over one million model repositories on platforms like Hugging Face [1], LLMs have evolved from research artifacts into critical software components powering applications from code generation to intelligent assistants. Zehao Wu and Y anjie Zhao contributed equally to this work. Haoyu Wang is the corresponding author (haoyuwang@hust.edu.cn). The full name of the authors' affiliation is Hubei Key Laboratory of Distributed System Security, Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology.