Quantum Machine Learning: Performance and Security Implications in Real-World Applications

• DOI: 10.48550/arxiv.2408.04543
• Publication Date: 2024-08-08
• Authors: Zhengping Luo; Tyler J. Stewart; Mourya Reddy Nara...; Rui Duan; Shangqing Zhao
• Keywords: FOS: Computer and information sciences; Quantum Physics; Computer Science - Machine Learning; FOS: Physical sciences; Quantum Physics (quant-ph); Machine Learning (cs.LG)

Quantum computing has garnered significant attention in recent years from both academia and industry due to its potential achieve a "quantum advantage" over classical computers. The advent of quantum introduces new challenges for security privacy. This poster explores the performance implications through case study machine learning real-world application. We compare (QML) algorithms their counterparts using Alzheimer's disease dataset. Our results indicate that QML show promising while they still have not surpassed terms capability convergence difficulty, running simulations on computers requires significantly large memory space CPU time. also indicates QMLs inherited vulnerabilities introduce attack vectors.