QTrojan: A Circuit Backdoor Against Quantum Neural Networks
This addresses security vulnerabilities in quantum machine learning for researchers and practitioners, though it is incremental as it builds on existing backdoor attack concepts.
The authors tackled the problem of backdoor attacks on Quantum Neural Networks (QNNs) by proposing QTrojan, a circuit-level attack that inserts quantum gates into the variational circuit, resulting in a 21% improvement in clean data accuracy and a 19.9% increase in attack success rate compared to prior methods.
We propose a circuit-level backdoor attack, \textit{QTrojan}, against Quantum Neural Networks (QNNs) in this paper. QTrojan is implemented by few quantum gates inserted into the variational quantum circuit of the victim QNN. QTrojan is much stealthier than a prior Data-Poisoning-based Backdoor Attack (DPBA), since it does not embed any trigger in the inputs of the victim QNN or require the access to original training datasets. Compared to a DPBA, QTrojan improves the clean data accuracy by 21\% and the attack success rate by 19.9\%.