Decentralized Unlearning for Trustworthy AI-Generated Content (AIGC) Services
- 6 August 2024
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Network
- Vol. 39 (3) , 285-292
Abstract
The widespread adoption of AI-Generated Content (AIGC) has captured remarkable interests from academia and industry. However, this advancement brings forth challenges in data ownership, as emphasized by the General Data Protection Regulation’s right to be forgotten. The right to be forgotten allows participants to erase their data contributions from well-trained AIGC models. Training AIGC models demands an extensive amount of data and computations, often surpassing the capabilities of individual participants. As a solution, Federated Learning (FL) is employed to collaboratively train an AIGC model without sharing raw data directly. To protect the right to be forgotten in FL, “federated unlearning” has been introduced to eradicate the data contributions of unlearning participants from fully trained AIGC models, achieved by deleting historical model updates. However, given that historical updates are distributed among various participants, they may still hold contributions from the unlearning participants. This presents a challenge to the trustworthiness of federated unlearning. In this paper, we first provide an overview of both centralized and federated learning and unlearning methods. We survey relevant works and classify four main categories for federated unlearning. Subsequently, we introduce a comprehensive decentralized unlearning architecture designed for trustworthy AIGC services. To address the challenge of participants retaining historical contributions from unlearning participants, we integrate a coded computing-based interaction mechanism, ensuring both scalability and security. We further present a case study using NanoGPT to demonstrate the effectiveness of the proposed framework for decentralized unlearning. We conclude by identifying potential future research directions.Keywords
Funding Information
- National Natural Science Foundation of China (62372050)
This publication has 13 references indexed in Scilit:
- FedME2: Memory Evaluation & Erase Promoting Federated Unlearning in DTMNIEEE Journal on Selected Areas in Communications, 2023
- FedRecovery: Differentially Private Machine Unlearning for Federated Learning FrameworksIEEE Transactions on Information Forensics and Security, 2023
- Federated Unlearning and Its Privacy ThreatsIEEE Network, 2023
- Asynchronous Federated Unlearning2023
- Blockchain-Aided Secure Semantic Communication for AI-Generated Content in MetaverseIEEE Open Journal of the Computer Society, 2023
- Federated Unlearning: Guarantee the Right of Clients to ForgetIEEE Network, 2022
- The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining2022
- Federated Unlearning via Class-Discriminative Pruning2022
- FedEraser: Enabling Efficient Client-Level Data Removal from Federated Learning Models2021
- Machine Unlearning2021