# Wireless Backdoor Attack and Defense for Semantic Communications over Multiple Access Channel

arXiv: https://arxiv.org/abs/2606.30595 · HTML: https://mlsanity.com/paper/2606.30595/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 17 references that are in the map.
- First posted on arXiv 29 Jun 2026.

## Builds on (most cited first, 11 of 11)

- [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)
- [Deep Joint Source-Channel Coding for Semantic Communications](https://mlsanity.com/paper/2211.08747/) (2022)
- [Semantic Communications in Networked Systems: A Data Significance Perspective](https://mlsanity.com/paper/2103.05391/) (2021)
- [Task-Oriented Communications for NextG: End-to-End Deep Learning and AI Security Aspects](https://mlsanity.com/paper/2212.09668/) (2022)
- [DeepMA: End-to-end Deep Multiple Access for Wireless Image Transmission in Semantic Communication](https://mlsanity.com/paper/2303.11543/) (2023)
- [Will 6G be Semantic Communications? Opportunities and Challenges from Task Oriented and Secure Communications to Integrated Sensing](https://mlsanity.com/paper/2401.01531/) (2024)
- [Vulnerabilities of Deep Learning-Driven Semantic Communications to Backdoor (Trojan) Attacks](https://mlsanity.com/paper/2212.11205/) (2022)
- [Non-Orthogonal Multiple Access Enhanced Multi-User Semantic Communication](https://mlsanity.com/paper/2303.06597/) (2023)
- [Backdoor Attacks and Defenses on Semantic-Symbol Reconstruction in Semantic Communications](https://mlsanity.com/paper/2404.13279/) (2024)
- [Multi-user Wireless Image Semantic Transmission over MIMO Multiple Access Channels](https://mlsanity.com/paper/2504.07969/) (2025)

## Abstract (arXiv)

Semantic communication (SemCom) aims to preserve semantic meaning and task-oriented information beyond conventional message recovery over wireless channels. The adoption of SemCom in shared-access wireless networks introduces new vulnerabilities for multi-user semantic inference. This paper considers a SemCom system for two transmitters communicating with a common receiver over a multiple access channel. Each transmitter maps source information into latent semantic representations, while the receiver jointly reconstructs and classifies the semantic information for both transmitters. A selective over-the-air backdoor (Trojan) attack is presented in which an adversary transmits a low-power trigger waveform over the air and injects it into the shared received signal during training. By transmitting the trigger again during testing, this stealthy, low-power attack selectively manipulates the semantic inference for one transmitter while minimally affecting the inference of the other transmitter. To mitigate this vulnerability, a trigger-aware defense mechanism is developed to preserve correct semantic labels under trigger-contaminated wireless observations. The results demonstrate both the vulnerability of shared-access SemCom systems to selective over-the-air backdoor attacks and the effectiveness of trigger-aware robust training for semantic protection.