Input-Aware Dynamic Backdoor Attack Against Quantum Neural Networks

Junrui Zhang, Zemin Chen, Lusi Li, Mohammad Ghasemigol, Daniel Takabi et al.|July 13, 2026arXiv

Key Takeaway

Quantum Neural Networks can be attacked with input-specific backdoors that are harder to detect than fixed-trigger attacks, and current QNN defenses are insufficient against this threat.

Summary

This paper introduces Q-DIBA, the first input-aware dynamic backdoor attack against Quantum Neural Networks. Unlike previous quantum backdoor attacks that use fixed triggers, Q-DIBA generates unique triggers for each input by jointly training a classical trigger generator with the victim QNN.

safety architecture

Key Terms

backdoor-attack quantum-neural-network trigger-generator density-matrix contrastive-learning