# Privacy-Preserving Semantic Communications via Multi-Task Learning and Adversarial Perturbations

arXiv: https://arxiv.org/abs/2512.24452 · HTML: https://mlsanity.com/paper/2512.24452/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 15 references that are in the map.
- First posted on arXiv 30 Dec 2025.

## Builds on (most cited first, 10 of 10)

- [Deep Learning Enabled Semantic Communication Systems](https://mlsanity.com/paper/2006.10685/) (2020)
- [Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communications](https://mlsanity.com/paper/2207.09353/) (2022)
- [A Survey on Semantic Communication Networks: Architecture, Security, and Privacy](https://mlsanity.com/paper/2405.01221/) (2024)
- [Task-Oriented Communications for NextG: End-to-End Deep Learning and AI Security Aspects](https://mlsanity.com/paper/2212.09668/) (2022)
- [Will 6G be Semantic Communications? Opportunities and Challenges from Task Oriented and Secure Communications to Integrated Sensing](https://mlsanity.com/paper/2401.01531/) (2024)
- [Encrypted Semantic Communication Using Adversarial Training for Privacy Preserving](https://mlsanity.com/paper/2209.09008/) (2022)
- [Deep Joint Source-Channel Coding for Image Transmission with Visual Protection](https://mlsanity.com/paper/2111.03234/) (2021)
- [SemProtector: A Unified Framework for Semantic Protection in Deep Learning-based Semantic Communication Systems](https://mlsanity.com/paper/2309.01386/) (2023)
- [Semantic-Enabled 6G Communication: A Task-oriented and Privacy-preserving Perspective](https://mlsanity.com/paper/2408.04188/) (2024)
- [Knowledge-Assisted Privacy Preserving in Semantic Communication](https://mlsanity.com/paper/2410.18418/) (2024)

## Abstract (arXiv)

Semantic communications conveys task-relevant meaning rather than focusing solely on message reconstruction, improving bandwidth efficiency and robustness for next-generation wireless systems. However, learned semantic representations can still leak sensitive information to unintended receivers (eavesdroppers). This paper presents a deep learning-based semantic communication framework that jointly supports multiple receiver tasks while explicitly limiting semantic leakage to an eavesdropper. The legitimate link employs a learned encoder at the transmitter, while the receiver trains decoders for semantic inference and data reconstruction. The security problem is formulated via an iterative min-max optimization in which an eavesdropper is trained to improve its semantic inference, while the legitimate transmitter-receiver pair is trained to preserve task performance while reducing the eavesdropper's success. We also introduce an auxiliary layer that superimposes a cooperative, adversarially crafted perturbation on the transmitted waveform to degrade semantic leakage to an eavesdropper. Performance is evaluated over Rayleigh fading channels with additive white Gaussian noise using MNIST and CIFAR-10 datasets. Semantic accuracy and reconstruction quality improve with increasing latent dimension, while the min-max mechanism reduces the eavesdropper's inference performance significantly without degrading the legitimate receiver. The perturbation layer is successful in reducing semantic leakage even when the legitimate link is trained only for its own task. This comprehensive framework motivates semantic communication designs with tunable, end-to-end privacy against adaptive adversaries in realistic wireless settings.