Communications in computer and information science

Quantum Neural Networks Under Threat: Modeling Security Risks and Attack Vectors

Nouhaila Innan, Walid El Maouaki, Alberto Marchisio, Muhammad Shafique

Published Jan 1, 2026• 1 citation

DOI: 10.1007/978-3-032-13855-2_12

Related papers

Research on detection and defense methods of backdoor attacks on quantum neural networks

Yulu Zhang

Security research in quantum neural networks (QNNs) is an emerging field that aims to utilize the principles of quantum mechanics to protect the security of neural networks, and this protection can be against different threats such as eavesdropping, tampering, and malware attacks. Backdoor attacks are a serious security challenge in the field of deep neural networks. This type of attack is highly stealthy and harmful, which can silently implant malicious functions and trigger them under specific conditions, thus disrupting the normal operation of neural networks or leaking sensitive information. To address the potential security risks of backdoor attacks to QNNs, this paper focuses on two core issues: backdoor attack detection and defense strategy design. It proposes an activation-based clustering method for backdoor sample detection (ACDM) to counter backdoor attack threats. Experimental results demonstrate that this defense method effectively safeguards the operational security of QNNs while enhancing the model's robustness against abnormal inputs and the reliability of its output results. It should be noted that the current research has limitations: the adaptability and effectiveness of this defense framework on complex high-dimensional datasets (e.g., quantum image datasets) and QNNs with different topological structures (e.g., deep quantum convolutional networks) require further validation and optimization through subsequent experiments.

Scientific ReportsJun 8, 20260 citations

Adversarial Threats in Quantum Machine Learning: A Survey of Attacks and Defenses

Archisman Ghosh, Satwik Kundu, Swaroop Ghosh

arXiv:2506.21842Quantum science and technologyJan 1, 20264 citations

Defending Quantum Neural Networks Against Adversarial Attacks with Homomorphic Data Encryption

Ellen Wang, Helena Chaine, Xiaodi Wang +2 more

Several studies have shown that quantum neural networks are susceptible to adversarial attacks, which pose a significant threat to the accuracy of quantum neural networks. Adversarial attacks may exploit the input data of a network by feeding incorrect data to a model while manipulating one that has already been trained, which may cause erroneous results. In this research, we propose a novel defense model to protect quantum neural networks against adversarial attacks by using homomorphic data encryption. Homomorphic encryption allows computations to be processed on encrypted data that has not yet been decrypted by converting the data into ciphertext, which allows the data to be handled in its original form without any risks of privacy breach. By incorporating homomorphic data encryption into quantum neural networks, our proposed model tries to reduce adversarial attacks that may perturb network outputs. Taken together, our approach sheds light on the future of quantum computing and the preservation of sensitive information.

International Conference on Computational Science and Computational Intelligence (CSCI)Dec 13, 20230 citations

Quantum Machine Learning: Perspectives in Cybersecurity

Davide Pastorello

Lecture notes in computer scienceJan 1, 20241 citation

Adversarial Attacks and Defence Mechanisms in Quantum Machine Learning Systems

Dzulfikar Ahmed, Mohamed Hafiz, SYED ABUTHAHIR +1 more

International Journal of Quantum Computing and Artificial Intelligence (IJQCAI)Jan 1, 20260 citations

Quantum-Enhanced Detection of False Base Stations in Beyond 5G Networks Using Quanvolutional Neural Network

I Wayan Adi Juliawan Pawana, Hoseok Kwon, Linawati Linawati +1 more

The emergence of Beyond 5G (B5G) and 6G networks introduces advanced capabilities in speed, latency, and connectivity, while also amplifying the risk of sophisticated security threats such as False Base Stations (FBS). These rogue entities imitate legitimate base stations to intercept data, perform man-in-the-middle attacks, or disrupt services. Researchers have explored conventional machine learning methods for FBS detection, but these methods often struggle to address the high-dimensional and dynamic nature of next-generation networks. This paper proposes a Quanvolutional Neural Network (QNN) framework as a quantum-enhanced solution for FBS detection. QNN utilizes quantum phenomena such as superposition and entanglement to perform complex feature transformations, enabling more expressive data representations than classical models. We evaluate the proposed QNN against a traditional Convolutional Neural Network (CNN) using a classification task designed to simulate the detection of FBS. Results demonstrate that although the QNN exhibits slower convergence during early training, it ultimately outperforms the CNN across all key evaluation metrics. The QNN achieves higher accuracy (90.65%), improved recall, lower false positive rate, and a superior F1 score, while also attaining a lower final training loss. These findings suggest that QNNs have strong potential for real-time, localized threat detection in AInative 6G architectures. Future work will explore deployment on Noisy Intermediate-Scale Quantum (NISQ) hardware and evaluate model performance under realistic noise conditions. This study contributes to ongoing research on integrating quantum machine learning into secure and intelligent wireless communication systems

International Conference on Smart-Green Technology in Electrical and Information Systems (ICSGTEIS)Oct 9, 20251 citation