Logo image
Back
Quantum Adversarial Attacks: Developing Quantum FGSM Algorithm
Conference proceeding   Peer reviewed

Quantum Adversarial Attacks: Developing Quantum FGSM Algorithm

Mst Shapna Akter, Hossain Shahriar, Alfredo Cuzzocrea and Fan Wu
Proceedings : annual International Computer Software and Applications Conference, pp.1073-1079
Annual Computers, Software, and Applications Conference (COMPSAC), 48th (Osaka, Japan, 07/02/2024–07/04/2024)
07/02/2024
DOI: https://doi.org/10.1109/COMPSAC61105.2024.00145
Web of Science ID: WOS:001308581200136

Metrics

1 Record Views
5 Times Cited - Web of Science

Abstract

Accuracy Adversarial Attack Artificial neural networks FGSM Measurement Neural Network (NN) QFGSM Quantum computing Quantum Neural Network (QNN) Computer Algorithms Electronic Neural Network Machine Learning Quantum Electronics Noise
Quantum machine learning, noted for its remarkable advancements in enhancing computational speed and augmenting data processing efficacy, is acquiring considerable recognition within the scientific community. Despite the noteworthy advancements of quantum machine learning, it shares with its traditional counterpart a susceptibility to adversarial threats. This presents a significant challenge and underscores the need for robust countermeasures in this emerging field of study. Developing effective adversarial attack algorithms, such as the Quantum Fast Gradient Sign Method (QFGSM), is crucial to opening the path for exploring robust defense mechanisms against these threats. However, unlike traditional machine learning, the quantum field currently lacks the effective techniques to orchestrate adversarial attacks. This study introduces and assesses the QFGSM, a adversarial attack algorithm tailored for QNNs. Additionally, we evaluate the effect of random noise and its quantum version on these models, providing a comprehensive comparison to understand the efficacy of adversarial attack methods. The evaluation is conducted on both traditional Neural Networks (NNs) and QNNs using the ClaMP dataset, a cybersecurity-focused dataset, and involves performance metrics like Accuracy, Precision, Recall, and F1 score. Our findings underscore the differential resilience of NNs and QNNs under adversarial attacks and reveal the contrasting effects of FGSM, QFGSM, and random noise-based methods. Our study reveals that Quantum Neural Networks (QNNs) show significant vulnerability to our proposed Quantum Fast Gradient Sign Method (QFGSM) compared to random noise, indicating a need for quantum-specific defenses in the face of this advanced adversarial attack algorithm.

Details

Logo image