# CAP: Detecting Unauthorized Data Usage in Generative Models via Prompt Generation

arXiv: https://arxiv.org/abs/2410.05819 · HTML: https://mlsanity.com/paper/2410.05819/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 26 references that are in the map.
- First posted on arXiv 8 Oct 2024.

## Builds on (most cited first, 12 of 12)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models](https://mlsanity.com/paper/1806.01246/) (2018)
- [DLFuzz: Differential Fuzzing Testing of Deep Learning Systems](https://mlsanity.com/paper/1808.09413/) (2018)
- [On Testing Machine Learning Programs](https://mlsanity.com/paper/1812.02257/) (2018)
- [Copyright Protection in Generative AI: A Technical Perspective](https://mlsanity.com/paper/2402.02333/) (2024)
- [Digger: Detecting Copyright Content Mis-usage in Large Language Model Training](https://mlsanity.com/paper/2401.00676/) (2024)
- [Muffin: Testing Deep Learning Libraries via Neural Architecture Fuzzing](https://mlsanity.com/paper/2204.08734/) (2022)
- [Survey of Security and Privacy Issues of Internet of Things](https://mlsanity.com/paper/1501.02211/) (2015)

## Abstract (arXiv)

To achieve accurate and unbiased predictions, Machine Learning (ML) models rely on large, heterogeneous, and high-quality datasets. However, this could raise ethical and legal concerns regarding copyright and authorization aspects, especially when information is gathered from the Internet. With the rise of generative models, being able to track data has become of particular importance, especially since they may (un)intentionally replicate copyrighted contents. Therefore, this work proposes Copyright Audit via Prompts generation (CAP), a framework for automatically testing whether an ML model has been trained with unauthorized data. Specifically, we devise an approach to generate suitable keys inducing the model to reveal copyrighted contents. To prove its effectiveness, we conducted an extensive evaluation campaign on measurements collected in four IoT scenarios. The obtained results showcase the effectiveness of CAP, when used against both realistic and synthetic datasets.