Superior resilience to poisoning and amenability to unlearning in quantum machine learning

TL;DR

This paper demonstrates that quantum machine learning models are inherently more resilient to data poisoning and more amenable to unlearning than classical models, due to fundamental differences in their response to data corruption.

Contribution

It reveals a fundamental difference in how classical and quantum neural networks handle data corruption, highlighting quantum models' resilience and suitability for efficient unlearning.

Findings

Quantum models show phase transition-like response to label noise.

Classical models exhibit brittle memorization of corrupted data.

Quantum models are more efficient for unlearning erroneous information.

Abstract

The reliability of artificial intelligence hinges on the integrity of its training data, a foundation often compromised by noise and corruption. Here, through a comparative study of classical and quantum neural networks on both classical and quantum data, we reveal a fundamental difference in their response to data corruption. We find that classical models exhibit brittle memorization, leading to a failure in generalization. In contrast, quantum models demonstrate remarkable resilience, which is underscored by a phase transition-like response to increasing label noise, revealing a critical point beyond which the model's performance changes qualitatively. We further establish and investigate the field of quantum machine unlearning, the process of efficiently forcing a trained model to forget corrupting influences. We show that the brittle nature of the classical model forms rigid, stubborn memories of erroneous data, making efficient unlearning challenging, while the quantum model is significantly more amenable to efficient forgetting with approximate unlearning methods. Our findings establish that quantum machine learning can possess a dual advantage of intrinsic resilience and efficient adaptability, providing a promising paradigm for the trustworthy and robust artificial intelligence of the future.