SoK Paper: Security Concerns in Quantum Machine Learning as a Service
Abstract
1 Introduction
1.1 Why QML Models are at Risk?
2 Background
2.1 Quantum Neural Network (QNN)
![](/cms/10.1145/3696843.3696846/asset/93e4a360-6018-4baa-80f5-c50f04d07194/assets/images/medium/hasp24-3-fig1.jpg)
2.2 Quantum Cloud Services
![](/cms/10.1145/3696843.3696846/asset/11f91192-f9f9-44ea-9455-b07fe1f84bb7/assets/images/medium/hasp24-3-fig2.jpg)
3 Training in QMLaaS
3.1 (Step-1) Data Pre-Processing
3.2 (Step-2) Design and Encode
3.3 (Step-3) Transpile and Map
3.4 (Step-4) Execute and Measure
3.5 (Step-5) Gradient Calculation
3.6 (Step-6) Parameter Optimization
4 Inferencing in QMLaaS
4.1 Hosting QML in Quantum-Classical Cloud
4.2 Inference Operation
5 Security Concerns
5.1 Assets in QMLaaS
5.1.1 Training/Testing Data.
5.1.2 Data Encoding Circuit.
5.1.3 PQC Architecture.
5.2 Adversary Motivation
5.3 Confidentiality
5.3.1 Threats from Classical Cloud.
5.3.2 Threats from Quantum Cloud.
![](/cms/10.1145/3696843.3696846/asset/9b68bc45-420f-4696-80bb-e24ac6f5bec2/assets/images/medium/hasp24-3-fig3.jpg)
5.4 Integrity
5.4.1 Threats from Classical Cloud.
5.4.2 Threats from Quantum Cloud.
5.5 Availability
5.5.1 Threats from Classical Cloud.
5.5.2 Threats from Quantum Cloud.
6 Conclusion
Acknowledgments
References
Index Terms
- SoK Paper: Security Concerns in Quantum Machine Learning as a Service
Recommendations
Machine learning in the quantum realm: The state-of-the-art, challenges, and future vision
AbstractMachine learning has become a ubiquitous and effective technique for data processing and classification. Furthermore, due to the superiority and progress of quantum computing in many areas (e.g., cryptography, machine learning, ...
Highlights- Organize the most recent research works to pave the way for QML researchers.
- ...
Supercomputing leverages quantum machine learning and Grover’s algorithm
AbstractThe complexity of searching algorithms in classical computing is a classic problem and a research area. Quantum computers and quantum algorithms can efficiently compute some classically hard problems. In addition, quantum machine learning ...
Quantum Machine Learning Applications in High-Energy Physics
ICCAD '22: Proceedings of the 41st IEEE/ACM International Conference on Computer-Aided DesignSome of the most significant achievements of the modern era of particle physics, such as the discovery of the Higgs boson, have been made possible by the tremendous effort in building and operating large-scale experiments like the Large Hadron Collider ...
Comments
Information & Contributors
Information
Published In
![cover image ACM Other conferences](/cms/asset/bfbbc7a0-6573-4490-9dd4-5df4296d8eee/3696843.cover.jpg)
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
Conference
Acceptance Rates
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 398Total Downloads
- Downloads (Last 12 months)398
- Downloads (Last 6 weeks)82
Other Metrics
Citations
View Options
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML FormatLogin options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in