A Channel-Triggered Backdoor Attack on Wireless Semantic Image Reconstruction

Computer Science > Cryptography and Security [Submitted on 31 Mar 2025 (v1), last revised 27 Mar 2026 (this version, v3)] A Channel-Triggered Backdoor Attack on Wireless Semantic Image Reconstruction Jialin Wan, Jinglong Shen, Nan Cheng, Zhisheng Yin, Yiliang Liu, Wenchao Xu, Xuemin (Sherman)Shen 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. Subjects: Cryptography and Security (cs.CR); Machine Learning (cs.LG) Cite as: arXiv:2503.23866 [cs.CR]   (or arXiv:2503.23866v3 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2503.23866 Focus to learn more Submission history From: Jialin Wan [view email] [v1] Mon, 31 Mar 2025 09:17:10 UTC (1,561 KB) [v2] Tue, 20 May 2025 09:41:52 UTC (1,722 KB) [v3] Fri, 27 Mar 2026 06:17:33 UTC (5,402 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2025-03 Change to browse by: cs cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)