Detecting Generative Parroting through Overfitting Masked Autoencoders
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929391690317824 |
|---|---|
| author | Taghanaki, Saeid Asgari Lambourne, Joseph |
| author_facet | Taghanaki, Saeid Asgari Lambourne, Joseph |
| contents | The advent of generative AI models has revolutionized digital content creation, yet it introduces challenges in maintaining copyright integrity due to generative parroting, where models mimic their training data too closely. Our research presents a novel approach to tackle this issue by employing an overfitted Masked Autoencoder (MAE) to detect such parroted samples effectively. We establish a detection threshold based on the mean loss across the training dataset, allowing for the precise identification of parroted content in modified datasets. Preliminary evaluations demonstrate promising results, suggesting our method's potential to ensure ethical use and enhance the legal compliance of generative models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_19050 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Detecting Generative Parroting through Overfitting Masked Autoencoders Taghanaki, Saeid Asgari Lambourne, Joseph Machine Learning Artificial Intelligence The advent of generative AI models has revolutionized digital content creation, yet it introduces challenges in maintaining copyright integrity due to generative parroting, where models mimic their training data too closely. Our research presents a novel approach to tackle this issue by employing an overfitted Masked Autoencoder (MAE) to detect such parroted samples effectively. We establish a detection threshold based on the mean loss across the training dataset, allowing for the precise identification of parroted content in modified datasets. Preliminary evaluations demonstrate promising results, suggesting our method's potential to ensure ethical use and enhance the legal compliance of generative models. |
| title | Detecting Generative Parroting through Overfitting Masked Autoencoders |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2403.19050 |