# A Channel-Triggered Backdoor Attack on Wireless Semantic Image Reconstruction

Source: [A Channel-Triggered Backdoor Attack on Wireless Semantic Image Reconstruction](<https://www.sota2.com/research/paper/68fa78a81e209131cea79acf>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-31T05:00:04.047Z

Authors: Jialin Wan, Jinglong Shen, Nan Cheng, Zhisheng Yin, Yiliang Liu, Wenchao Xu, Xuemin (Sherman) Shen

Published: 2025-03-31T09:17:10.000Z

## Abstract

This paper investigates backdoor attacks in image-oriented semantic communications. The threat of backdoor attacks on symbol reconstruction in semantic communication (SemCom) systems has received limited attention. Previous research on backdoor attacks targeting SemCom symbol reconstruction primarily focuses on input-level triggers, which are impractical in scenarios with strict input constraints. In this paper, we propose a novel channel-triggered backdoor attack (CT-BA) framework that exploits inherent wireless channel characteristics as activation triggers. Our key innovation involves utilizing fundamental channel statistics parameters, specifically channel gain with different fading distributions or channel noise with different power, as potential triggers. This approach enhances stealth by eliminating explicit input manipulation, provides flexibility through trigger selection from diverse channel conditions, and enables automatic activation via natural channel variations without adversary intervention. We extensively evaluate CT-BA across four joint source-channel coding (JSCC) communication system architectures and three benchmark datasets. Simulation results demonstrate that our attack achieves near-perfect attack success rate (ASR) while maintaining effective stealth. Finally, we discuss potential defense mechanisms against such attacks.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Semantic Image Reconstruction Backdoor Attack on CIFAR-10](<https://www.sota2.com/research/sota/semantic-image-reconstruction-backdoor-attack-on-cifar-10.md>): Backdoor Attack on Semantic Image Reconstruction; CIFAR-10; PSNRb: 57.04.

- [Backdoor Attack on Semantic Image Reconstruction on MNIST](<https://www.sota2.com/research/sota/backdoor-attack-on-semantic-image-reconstruction-on-mnist.md>): Backdoor Attack on Semantic Image Reconstruction; MNIST; PSNR (Backdoor): 61.47.

- [Backdoor Attack on Semantic Image Reconstruction on ImageNet](<https://www.sota2.com/research/sota/backdoor-attack-on-semantic-image-reconstruction-on-imagenet.md>): Backdoor Attack on Semantic Image Reconstruction; ImageNet; PSNRb: 34.24.

- [Semantic Image Reconstruction on ImageNet (test)](<https://www.sota2.com/research/sota/semantic-image-reconstruction-on-imagenet-test.md>): Semantic Image Reconstruction; ImageNet (test); PSNR (Background) (dB): 34.09.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2503.23866>)

[PDF](<https://arxiv.org/pdf/2503.23866.pdf>)