SCU: An Efficient Machine Unlearning Scheme for Deep Learning Enabled Semantic Communications

2025-02-27

IEEE Transactions on Information Forensics and Security

AI Summary

To address the challenge of user data removal in deep learning-based semantic communication, this paper proposes the first machine unlearning framework tailored for jointly trained unsupervised encoders and decoders. Our method introduces (1) a mutual information minimization mechanism to enable targeted forgetting at the semantic representation level, and (2) a contrastive compensation strategy that restores model utility without accessing original training data. Crucially, the approach avoids full retraining or data reconstruction, substantially reducing deployment overhead. Extensive experiments on three benchmark datasets demonstrate that, after unlearning: residual influence remains below 1%, PSNR and SSIM degradation is under 0.8%, and inference latency drops by 62%. The framework thus achieves a favorable trade-off among security (effective forgetting), utility (preserved reconstruction quality), and efficiency (low computational cost).

Technology Category

• Machine Learning: Unsupervised & Self-Supervised Learning
• Search and Optimization: Learning to Search
• Computer Vision: Learning & Optimization for CV

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Deep learning (DL) enabled semantic communications leverage DL to train encoders and decoders (codecs) to extract and recover semantic information. However, most semantic training datasets contain personal private information. Such concerns call for enormous requirements for specified data erasure from semantic codecs when previous users hope to move their data from the semantic system. Existing machine unlearning solutions remove data contribution from trained models, yet usually in supervised sole model scenarios. These methods are infeasible in semantic communications that often need to jointly train unsupervised encoders and decoders. In this paper, we investigate the unlearning problem in DL-enabled semantic communications and propose a semantic communication unlearning (SCU) scheme to tackle the problem. SCU includes two key components. Firstly, we customize the joint unlearning method for semantic codecs, including the encoder and decoder, by minimizing mutual information between the learned semantic representation and the erased samples. Secondly, to compensate for semantic model utility degradation caused by unlearning, we propose a contrastive compensation method, which considers the erased data as the negative samples and the remaining data as the positive samples to retrain the unlearned semantic models contrastively. Theoretical analysis and extensive experimental results on three representative datasets demonstrate the effectiveness and efficiency of our proposed methods.

Problem

• Machine unlearning in semantic communications
• Joint unlearning for encoders and decoders
• Compensating semantic model utility degradation

Innovation

• Joint unlearning for semantic codecs
• Contrastive compensation method
• Minimizing mutual information effectively