# Privacy-Aware Communication Over a Wiretap Channel with Generative Networks

arXiv: https://arxiv.org/abs/2110.04094 · HTML: https://mlsanity.com/paper/2110.04094/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 24 references that are in the map.
- First posted on arXiv 8 Oct 2021.

## Builds on (most cited first, 6 of 6)

- [On Variational Bounds of Mutual Information](https://mlsanity.com/paper/1905.06922/) (2019)
- [An Introduction to Deep Learning for the Physical Layer](https://mlsanity.com/paper/1702.00832/) (2017)
- [Machine Learning in the Air](https://mlsanity.com/paper/1904.12385/) (2019)
- [The Best Defense Is a Good Offense: Adversarial Attacks to Avoid Modulation Detection](https://mlsanity.com/paper/1902.10674/) (2019)
- [Privacy-Aware Time-Series Data Sharing with Deep Reinforcement Learning](https://mlsanity.com/paper/2003.02685/) (2020)
- [Active Privacy-utility Trade-off Against a Hypothesis Testing Adversary](https://mlsanity.com/paper/2102.08308/) (2021)

## Built on by (most cited first, 7 of 7)

- [Generative Joint Source-Channel Coding for Semantic Image Transmission](https://mlsanity.com/paper/2211.13772/) (2022)
- [CommIN: Semantic Image Communications as an Inverse Problem with INN-Guided Diffusion Models](https://mlsanity.com/paper/2310.01130/) (2023)
- [Secure Deep-JSCC Against Multiple Eavesdroppers](https://mlsanity.com/paper/2308.02892/) (2023)
- [SING: Semantic Image Communications using Null-Space and INN-Guided Diffusion Models](https://mlsanity.com/paper/2503.12484/) (2025)
- [Active Privacy-Utility Trade-off Against Inference in Time-Series Data Sharing](https://mlsanity.com/paper/2202.05833/) (2022)
- [Adaptive Dual-Path Framework for Covert Semantic Communication](https://mlsanity.com/paper/2605.03423/) (2026)
- [Privacy-Preserving Deep Joint Source-Channel Coding with In-Loop Concept Erasure](https://mlsanity.com/paper/2609.13393/) (2026)

## Abstract (arXiv)

We study privacy-aware communication over a wiretap channel using end-to-end learning. Alice wants to transmit a source signal to Bob over a binary symmetric channel, while passive eavesdropper Eve tries to infer some sensitive attribute of Alice's source based on its overheard signal. Since we usually do not have access to true distributions, we propose a data-driven approach using variational autoencoder (VAE)-based joint source channel coding (JSCC). We show through simulations with the colored MNIST dataset that our approach provides high reconstruction quality at the receiver while confusing the eavesdropper about the latent sensitive attribute, which consists of the color and thickness of the digits. Finally, we consider a parallel-channel scenario, and show that our approach arranges the information transmission such that the channels with higher noise levels at the eavesdropper carry the sensitive information, while the non-sensitive information is transmitted over more vulnerable channels.