Ensuring superior learning outcomes and data security for authorized learner
arXiv:2501.00754 · doi:10.1088/2058-9565/adc501
Abstract
The learner's ability to generate a hypothesis that closely approximates the target function is crucial in machine learning. Achieving this requires sufficient data; however, unauthorized access by an eavesdropping learner can lead to security risks. Thus, it is important to ensure the performance of the "authorized" learner by limiting the quality of the training data accessible to eavesdroppers. Unlike previous studies focusing on encryption or access controls, we provide a theorem to ensure superior learning outcomes exclusively for the authorized learner with quantum label encoding. In this context, we use the probably-approximately-correct (PAC) learning framework and introduce the concept of learning probability to quantitatively assess learner performance. Our theorem allows the condition that, given a training dataset, an authorized learner is guaranteed to achieve a certain quality of learning outcome, while eavesdroppers are not. Notably, this condition can be constructed based only on the authorized-learning-only measurable quantities of the training data, i.e., its size and noise degree. We validate our theoretical proofs and predictions through convolutional neural networks (CNNs) image classification learning.
17 pages, 7 figures, comments welcome
References in corpus (22)
- Quantum Machine Learning
- Supervised learning with quantum enhanced feature spaces
- Quantum support vector machine for big data classification
- Quantum machine learning in feature Hilbert spaces
- Quantum principal component analysis
- Quantum cloning
- Quantum machine learning: a classical perspective
- Prediction by linear regression on a quantum computer
- Quantum noise protects quantum classifiers against adversaries
- Quantum Algorithm for Linear Regression
- Quantum machine learning for quantum anomaly detection
- Quantum principal component analysis only achieves an exponential speedup because of its state preparation assumptions
- On the robustness of bucket brigade quantum RAM
- Data centers with quantum random access memory and quantum networks
- Quantum Data Center: Perspectives
- Protocol for secure quantum machine learning at a distant place
- Experimental demonstration of quantum learning speed-up with classical input data
- Optimal Broadcasting of Mixed States
- Optimal eavesdropping on QKD without quantum memory
- Quantum secure learning with classical samples
- Tangible reduction in learning sample complexity with large classical samples and small quantum system
- Quantum multi-anomaly detection