A Channel-Triggered Backdoor Attack on Wireless Semantic Image Reconstruction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914426151501824 |
|---|---|
| author | Wan, Jialin Shen, Jinglong Cheng, Nan Yin, Zhisheng Liu, Yiliang Xu, Wenchao Xuemin Shen |
| author_facet | Wan, Jialin Shen, Jinglong Cheng, Nan Yin, Zhisheng Liu, Yiliang Xu, Wenchao Xuemin Shen |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_23866 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Channel-Triggered Backdoor Attack on Wireless Semantic Image Reconstruction Wan, Jialin Shen, Jinglong Cheng, Nan Yin, Zhisheng Liu, Yiliang Xu, Wenchao Xuemin Shen Cryptography and Security Machine Learning 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. |
| title | A Channel-Triggered Backdoor Attack on Wireless Semantic Image Reconstruction |
| topic | Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2503.23866 |