Bang, Jeongho Song, Wooyeong Shin, Kyujin Kim, Yong-Su 2025-04-25T06:01:15Z 2025-04-25T06:01:15Z 2025-04-25 2025-04 2058-9565 https://pubs.kist.re.kr/handle/201004/152303 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 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 image classification learning. English IOP PUBLISHING LTD Ensuring superior learning outcomes and data security for authorized learner Article 10.1088/2058-9565/adc501 1 Quantum Science and Technology, v.10, no.2 Quantum Science and Technology 10 2 N scie scopus 001458722500001 2-s2.0-105002420603 Quantum Science & Technology Physics, Multidisciplinary Physics Article QUANTUM INFORMATION quantum secure machine learning quantum data encoding quantum data security