paper-with-me

홈 › Papers

Detecting Generative Parroting through Overfitting Masked Autoencoders

2024-03-27 · Saeid Asgari Taghanaki, Joseph Lambourne

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.

📄 PDF Abstract BibTeX arXiv:2403.19050

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Context parroting: A simple but tough-to-beat baseline for foundation models in scientific machine learning

2025-05-16 · Yuanzhao Zhang, William Gilpin

Recently-developed time series foundation models for scientific machine learning exhibit emergent abilities to predict physical systems. These abilities include zero-shot forecasting, in which a model forecasts future st…

In-Context LearningTime SeriesTime Series Forecasting

A Non-Parametric Test to Detect Data-Copying in Generative Models

2020-04-12 · Casey Meehan, Kamalika Chaudhuri, Sanjoy Dasgupta

Detecting overfitting in generative models is an important challenge in machine learning. In this work, we formalize a form of overfitting that we call {\em{data-copying}} -- where the generative model memorizes and outp…

BIG-bench Machine Learning

MotionDreamer: One-to-Many Motion Synthesis with Localized Generative Masked Transformer

2025-04-11 · Yilin Wang, Chuan Guo, Yuxuan Mu, Muhammad Gohar Javed 외

Generative masked transformers have demonstrated remarkable success across various content generation tasks, primarily due to their ability to effectively model large-scale dataset distributions with high consistency. Ho…

Motion SynthesisQuantization

Polly Want a Cracker: Analyzing Performance of Parroting on Paraphrase Generation Datasets

2019-08-19 · IJCNLP 2019 11 · Hongren Mao, Hung-Yi Lee

Paraphrase generation is an interesting and challenging NLP task which has numerous practical applications. In this paper, we analyze datasets commonly used for paraphrase generation research, and show that simply parrot…

Paraphrase GenerationSentence

Detecting Overfitting of Deep Generative Networks via Latent Recovery

2019-01-09 · CVPR 2019 6 · Ryan Webster, Julien Rabin, Loic Simon, Frederic Jurie

State of the art deep generative networks are capable of producing images with such incredible realism that they can be suspected of memorizing training images. It is why it is not uncommon to include visualizations of t…

Facial InpaintingMemorizationSuper-Resolution