Secure PAC Learning: Sample-Budget Laws and Quantum Data-Path Admissibility

TL;DR

This paper develops a comprehensive framework for secure PAC learning that integrates security guarantees with sample-budget laws, especially in quantum settings, establishing quantum-specific security criteria and operational bounds.

Contribution

It introduces a novel secure PAC learning theory linking data-path admissibility to sample budgets, including quantum-specific security measures based on Holevo information.

Findings

Quantum-secure PAC learning framework established

Sample-budget bounds guarantee learning success under security constraints

Quantum data-path admissibility is characterized by Holevo information

Abstract

Security in machine learning is fragile when data are exfiltrated or perturbed, yet existing frameworks rarely connect the definition and analysis of the security to learnability. In this work, we develop a theory of secure learning grounded in the probably-approximately-correct (PAC) viewpoint and develop an operational framework that links data-path behavior to finite-sample budgets. In our formulation, an accuracy-confidence target is evaluated via a run-based sequential test that halts after a prescribed number of consecutive validations, and a closed-form budget bound guarantees the learning success if the data-path channel is admissible; the acceptance must also exceed a primitive random-search baseline. We elevate and complete our secure-learning construction in the context of quantum information -- establishing quantum-secure PAC learning: for prepare-and-measure scenarios, the data-path admissibility is set to be threshold fixed by Holevo information, not a learner-tunable tolerance. Thus, a certified information advantage for the learner directly becomes the learning security -- an effect with no classical analogue. The channel-determined confidence follows naturally and basis sifting is incorporated for practical deployments. This is the first complete framework that simultaneously embeds a security notion and an operational sample-budget law within the PAC learning and anchors the security in quantum information. The resulting blueprint points toward standardized guarantees for the learning security, with clear avenues for PAC-Bayes extensions and for integration with advanced quantum machine learning front ends.