Matrix-Driven Instant Review: Confident Detection and Reconstruction of LLM Plagiarism on PC

📅 2025-08-08
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
Existing LLM weight plagiarism detection methods suffer from inaccurate weight mapping reconstruction, lack of statistically rigorous significance measures (e.g., *p*-values), and high false-positive rates due to training data similarity. Method: This paper proposes a novel detection framework grounded in matrix analysis and large deviations theory. It integrates spectral alignment with matrix similarity analysis—requiring neither model inference nor full weight loading—and reconstructs cross-model weight relationships interpretably using only inter-layer weight matrix structure, while providing theoretically grounded statistical significance assessment (*p*-values). Contributions/Results: Experiments demonstrate strong robustness against severe perturbations—including random weight permutation, structured pruning, and trillion-token-scale continued pretraining—while achieving sub-hour full-model detection on a single PC. The method significantly outperforms state-of-the-art approaches in both accuracy and reliability.

Technology Category

Application Category

📝 Abstract
In recent years, concerns about intellectual property (IP) in large language models (LLMs) have grown significantly. Plagiarizing other LLMs (through direct weight copying, upcycling, pruning, or continual pretraining) and claiming authorship without properly attributing to the original license, is a serious misconduct that can lead to significant financial and reputational harm to the original developers. However, existing methods for detecting LLM plagiarism fall short in key areas. They fail to accurately reconstruct weight correspondences, lack the ability to compute statistical significance measures such as $p$-values, and may mistakenly flag models trained on similar data as being related. To address these limitations, we propose Matrix-Driven Instant Review (MDIR), a novel method that leverages matrix analysis and Large Deviation Theory. MDIR achieves accurate reconstruction of weight relationships, provides rigorous $p$-value estimation, and focuses exclusively on weight similarity without requiring full model inference. Experimental results demonstrate that MDIR reliably detects plagiarism even after extensive transformations, such as random permutations and continual pretraining with trillions of tokens. Moreover, all detections can be performed on a single PC within an hour, making MDIR both efficient and accessible.
Problem

Research questions and friction points this paper is trying to address.

Detects LLM plagiarism without full model inference
Reconstructs weight relationships accurately and efficiently
Computes statistical significance measures like p-values
Innovation

Methods, ideas, or system contributions that make the work stand out.

Matrix analysis for weight relationship reconstruction
Large Deviation Theory for p-value estimation
Efficient detection on a single PC