English

Toward Polymorphic Backdoor against Semantic Communication via Intensity-Based Poisoning

Cryptography and Security 2026-04-28 v1 Artificial Intelligence

Abstract

Semantic Communication (SC) backdoor attacks aim to utilize triggers to manipulate the system into producing predetermined outputs via backdoored shared knowledge. Current SC backdoors adopt monomorphic paradigms with single attack target, which suffers from limited attack diversity, efficiency, and flexibility in heterogeneous downstream scenarios. To overcome the limitations, we propose SemBugger, a polymorphic SC backdoor. By dynamically adjusting the trigger intensity, SemBugger finely-grained controls over the SC knowledge to generate diverse malicious results from the system. Specifically, SemBugger is realized through a multi-effect poisoning-training framework. It introduces graded-intensity triggers to poison training data and optimizes SC systems with hierarchical malicious loss. The trained system's knowledge dynamically adapts to trigger intensity in inputs to yield target outputs, all while preserving transmission fidelity for benign samples. Moreover, to augment SC security, we propose a provable robustness defense that resists SemBugger's homogeneous attacks through a controlled noise mechanism. It operates via strategically adding noise in SC inputs, and we formally provide a theoretical lower bound on the defense efficacy. Experiments across diverse SC models and benchmark datasets indicate that SemBugger attains high attack efficacy while maintaining the regular functionality of SC systems. Meanwhile, the designed defense effectively neutralizes SemBugger attacks.

Keywords

Cite

@article{arxiv.2604.23231,
  title  = {Toward Polymorphic Backdoor against Semantic Communication via Intensity-Based Poisoning},
  author = {Xiao Yang and Yuni Lai and Gaolei Li and Jun Wu and Kai Zhou and Jianhua Li and Mingzhe Chen},
  journal= {arXiv preprint arXiv:2604.23231},
  year   = {2026}
}

Comments

This paper has been accepted by IEEE TIFS

R2 v1 2026-07-01T12:34:58.502Z