paper-with-me

홈 › Papers

Machine Unlearning for Image-to-Image Generative Models

2024-02-01 · Guihong Li, Hsiang Hsu, Chun-Fu Chen, Radu Marculescu

Machine unlearning has emerged as a new paradigm to deliberately forget data samples from a given model in order to adhere to stringent regulations. However, existing machine unlearning methods have been primarily focused on classification models, leaving the landscape of unlearning for generative models relatively unexplored. This paper serves as a bridge, addressing the gap by providing a unifying framework of machine unlearning for image-to-image generative models. Within this framework, we propose a computationally-efficient algorithm, underpinned by rigorous theoretical analysis, that demonstrates negligible performance degradation on the retain samples, while effectively removing the information from the forget samples. Empirical studies on two large-scale datasets, ImageNet-1K and Places-365, further show that our algorithm does not rely on the availability of the retain samples, which further complies with data retention policy. To our best knowledge, this work is the first that represents systemic, theoretical, empirical explorations of machine unlearning specifically tailored for image-to-image generative models. Our code is available at https://github.com/jpmorganchase/l2l-generator-unlearning.

📄 PDF Abstract BibTeX arXiv:2402.00351

Code (2)

jpmorganchase/i2i-generator-unlearning 공식 구현 pytorch
jpmorganchase/l2l-generator-unlearning 공식 구현 pytorch

Tasks

Machine Unlearning

Similar Papers 제목 키워드 기반

Controllable Unlearning for Image-to-Image Generative Models via $\varepsilon$-Constrained Optimization

2024-08-03 · Xiaohua Feng, Chaochao Chen, Yuyuan Li, Li Zhang

While generative models have made significant advancements in recent years, they also raise concerns such as privacy breaches and biases. Machine unlearning has emerged as a viable solution, aiming to remove specific tra…

Machine Unlearningvalid

On the Limitations and Prospects of Machine Unlearning for Generative AI

2024-08-01 · Shiji Zhou, Lianzhe Wang, Jiangnan Ye, Yongliang Wu 외

Generative AI (GenAI), which aims to synthesize realistic and diverse data samples from latent variables or other data modalities, has achieved remarkable results in various domains, such as natural language, images, aud…

EthicsMachine Unlearning

Generative Unlearning for Any Identity

2024-05-16 · CVPR 2024 1 · Juwon Seo, Sung-Hoon Lee, Tae-Young Lee, Seungjun Moon 외

Recent advances in generative models trained on large-scale datasets have made it possible to synthesize high-quality samples across various domains. Moreover, the emergence of strong inversion networks enables not only …

Machine Unlearning

Realistic Image-to-Image Machine Unlearning via Decoupling and Knowledge Retention

2025-02-06 · Ayush K. Varshney, Vicenç Torra

Machine Unlearning allows participants to remove their data from a trained machine learning model in order to preserve their privacy, and security. However, the machine unlearning literature for generative models is rath…

Machine Unlearning

Boosting Alignment for Post-Unlearning Text-to-Image Generative Models

2024-12-09 · Myeongseob Ko, Henry Li, Zhun Wang, Jonathan Patsenker 외

Large-scale generative models have shown impressive image-generation capabilities, propelled by massive data. However, this often inadvertently leads to the generation of harmful or inappropriate content and raises copyr…

Image GenerationMachine Unlearning