Who Stole Your Data? A Method for Detecting Unauthorized RAG Theft
Retrieval-augmented generation (RAG) enhances Large Language Models (LLMs) by mitigating hallucinations and outdated information issues, yet simultaneously facilitates unauthorized data appropriation at scale. This paper addresses this challenge through two key contributions. First, we introduce RPD, a novel dataset specifically designed for RAG plagiarism detection that encompasses diverse professional domains and writing styles, overcoming limitations in existing resources. Second, we develop a dual-layered watermarking system that embeds protection at both semantic and lexical levels, complemented by an interrogator-detective framework that employs statistical hypothesis testing on accumulated evidence. Extensive experimentation demonstrates our approach's effectiveness across varying query volumes, defense prompts, and retrieval parameters, while maintaining resilience against adversarial evasion techniques. This work establishes a foundational framework for intellectual property protection in retrieval-augmented AI systems.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
A Non-Intrusive Machine Learning Solution for Malware Detection and Data Theft Classification in Smartphones
Smartphones contain information that is more sensitive and personal than those found on computers and laptops. With an increase in the versatility of smartphone functionality, more data has become vulnerable and exposed …
BIG-bench Machine LearningMalware DetectionWatermarking One for All: A Robust Watermarking Scheme Against Partial Image Theft
The proliferation of digital images on the Internet has provided unprecedented convenience, but also poses significant risks of malicious theft and misuse. Digital watermarking has long been researched as an effectiv…
AllSteal My Artworks for Fine-tuning? A Watermarking Framework for Detecting Art Theft Mimicry in Text-to-Image Models
The advancement in text-to-image models has led to astonishing artistic performances. However, several studios and websites illegally fine-tune these models using artists' artworks to mimic their styles for profit, which…
Garbage in, model out: Weight theft with just noise
This paper explores the scenarios under which an attacker can claim that ‘Noise and access to the softmax layer of the model is all you need’ to steal the weights of a convolutional neural network whose architecture is a…
Model Weight Theft With Just Noise Inputs: The Curious Case of the Petulant Attacker
This paper explores the scenarios under which an attacker can claim that 'Noise and access to the softmax layer of the model is all you need' to steal the weights of a convolutional neural network whose architecture is a…