# Diffusion-aided Task-oriented Semantic Communications with Model Inversion Attack

arXiv: https://arxiv.org/abs/2506.19886 · HTML: https://mlsanity.com/paper/2506.19886/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 61 references that are in the map.
- First posted on arXiv 24 Jun 2025.

## Builds on (most cited first, 30 of 31)

- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Diffusion Models: A Comprehensive Survey of Methods and Applications](https://mlsanity.com/paper/2209.00796/) (2022)
- [Diffusion Models in Vision: A Survey](https://mlsanity.com/paper/2209.04747/) (2022)
- [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)
- [CDDM: Channel Denoising Diffusion Models for Wireless Semantic Communications](https://mlsanity.com/paper/2309.08895/) (2023)
- [Wireless Deep Video Semantic Transmission](https://mlsanity.com/paper/2205.13129/) (2022)
- [Generative Semantic Communication: Diffusion Models Beyond Bit Recovery](https://mlsanity.com/paper/2306.04321/) (2023)
- [Adversarial Learning of Privacy-Preserving and Task-Oriented Representations](https://mlsanity.com/paper/1911.10143/) (2019)
- [Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses](https://mlsanity.com/paper/2402.04013/) (2024)
- [Deep Joint Source-Channel Coding for Adaptive Image Transmission over MIMO Channels](https://mlsanity.com/paper/2309.00470/) (2023)
- [Resource allocation for text semantic communications](https://mlsanity.com/paper/2201.06023/) (2022)
- [Privacy-preserving Adversarial Facial Features](https://mlsanity.com/paper/2305.05391/) (2023)
- [Semantic Communication Meets Edge Intelligence](https://mlsanity.com/paper/2202.06471/) (2022)
- [Diffusion-Driven Semantic Communication for Generative Models with Bandwidth Constraints](https://mlsanity.com/paper/2407.18468/) (2024)
- [A new communication paradigm: from bit accuracy to semantic fidelity](https://mlsanity.com/paper/2101.12649/) (2021)
- [Semantic Communications for Image Recovery and Classification via Deep Joint Source and Channel Coding](https://mlsanity.com/paper/2304.02317/) (2023)
- [TIPRDC: Task-Independent Privacy-Respecting Data Crowdsourcing Framework for Deep Learning with Anonymized Intermediate Representations](https://mlsanity.com/paper/2005.11480/) (2020)
- [Diffusion models for audio semantic communication](https://mlsanity.com/paper/2309.07195/) (2023)
- [Direction-Oriented Visual-semantic Embedding Model for Remote Sensing Image-text Retrieval](https://mlsanity.com/paper/2310.08276/) (2023)
- [Semantic Information Recovery in Wireless Networks](https://mlsanity.com/paper/2204.13366/) (2022)
- [Deep Joint Source-Channel Coding for Wireless Image Retrieval](https://mlsanity.com/paper/1910.12703/) (2019)
- [Secure Semantic Communications: Fundamentals and Challenges](https://mlsanity.com/paper/2301.01421/) (2023)
- [End-to-End Learning for Task-Oriented Semantic Communications Over MIMO Channels: An Information-Theoretic Framework](https://mlsanity.com/paper/2408.17397/) (2024)
- [The Model Inversion Eavesdropping Attack in Semantic Communication Systems](https://mlsanity.com/paper/2308.04304/) (2023)
- [Reaching Data Confidentiality and Model Accountability on the CalTrain](https://mlsanity.com/paper/1812.03230/) (2018)
- [Online Resource Allocation for Semantic-Aware Edge Computing Systems](https://mlsanity.com/paper/2309.13917/) (2023)
- [Video Semantic Communication with Major Object Extraction and Contextual Video Encoding](https://mlsanity.com/paper/2402.01330/) (2024)
- [Secure Semantic Communication for Image Transmission in the Presence of Eavesdroppers](https://mlsanity.com/paper/2404.12170/) (2024)
- [Contrastive Learning and Adversarial Disentanglement for Privacy-Aware Task-Oriented Semantic Communication](https://mlsanity.com/paper/2410.22784/) (2024)

## Built on by (most cited first, 1 of 1)

- [Predictive-State Communication: Innovation Coding and Reconciliation under Delay](https://mlsanity.com/paper/2602.10542/) (2026)

## Abstract (arXiv)

Semantic communication enhances transmission efficiency by conveying semantic information rather than raw input symbol sequences. Task-oriented semantic communication further aims to retain only task-specific information, thereby achieving greater bandwidth savings. However, these neural-network-based communication systems are vulnerable to model inversion attacks, in which adversaries attempt to recover sensitive input information from intercepted semantic features. The key challenge is therefore to preserve privacy while maintaining task accuracy and robustness. We consider a task-confidential setting in which the adversary attempts to reconstruct the original input from intercepted features without knowing the legitimate receiver's task or model. Although PSNR and SSIM are commonly used to assess reconstruction quality, we find that an external classifier can still perform the legitimate receiver's task with nontrivial accuracy on reconstructions with low PSNR or SSIM, indicating that these reconstructions still contain task-level semantic leakage. We therefore propose DiffSem, which splits the diffusion process between controlled transmitter-side self-noising and matched receiver-side reverse denoising. Experiments on the MNIST, CIFAR-10, and CelebA datasets show that DiffSem improves the legitimate receiver's task accuracy without increasing either the transmitted feature size or information leakage.