# Quantum Machine Unlearning: Foundations, Mechanisms, and Taxonomy

arXiv: https://arxiv.org/abs/2511.00406 · HTML: https://mlsanity.com/paper/2511.00406/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 41 of its 139 references that are in the map.
- First posted on arXiv 1 Nov 2025.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 30 of 41)

- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Barren plateaus in quantum neural network training landscapes](https://mlsanity.com/paper/1803.11173/) (2018)
- [Certified Data Removal from Machine Learning Models](https://mlsanity.com/paper/1911.03030/) (2019)
- [Making AI Forget You: Data Deletion in Machine Learning](https://mlsanity.com/paper/1907.05012/) (2019)
- [Quantum Natural Gradient](https://mlsanity.com/paper/1909.02108/) (2019)
- [Explaining Quantum Circuits with Shapley Values: Towards Explainable Quantum Machine Learning](https://mlsanity.com/paper/2301.09138/) (2023)
- [Federated Quantum Machine Learning with Differential Privacy](https://mlsanity.com/paper/2310.06973/) (2023)
- [Quantum Kernel-Based Long Short-term Memory for Climate Time-Series Forecasting](https://mlsanity.com/paper/2412.08851/) (2024)
- [Privacy-preserving quantum federated learning via gradient hiding](https://mlsanity.com/paper/2312.04447/) (2023)
- [Federated Quantum Long Short-term Memory (FedQLSTM)](https://mlsanity.com/paper/2312.14309/) (2023)
- [Toward Large-Scale Distributed Quantum Long Short-Term Memory with Modular Quantum Computers](https://mlsanity.com/paper/2503.14088/) (2025)
- [CompressedMediQ: Hybrid Quantum Machine Learning Pipeline for High-Dimensional Neuroimaging Data](https://mlsanity.com/paper/2409.08584/) (2024)
- [Benchmarking quantum machine learning kernel training for classification tasks](https://mlsanity.com/paper/2408.10274/) (2024)
- [Optimal training of finitely-sampled quantum reservoir computers for forecasting of chaotic dynamics](https://mlsanity.com/paper/2409.01394/) (2024)
- [Quantum Federated Learning With Quantum Networks](https://mlsanity.com/paper/2310.15084/) (2023)
- [Applying Quantum Autoencoders for Time Series Anomaly Detection](https://mlsanity.com/paper/2410.04154/) (2024)
- [AI-driven Reverse Engineering of QML Models](https://mlsanity.com/paper/2408.16929/) (2024)
- [Lorentz-Equivariant Quantum Graph Neural Network for High-Energy Physics](https://mlsanity.com/paper/2411.01641/) (2024)
- [Q-Fusion: Diffusing Quantum Circuits](https://mlsanity.com/paper/2504.20794/) (2025)
- [On the Principles of Differentiable Quantum Programming Languages](https://mlsanity.com/paper/2004.01122/) (2020)
- [Image Classification with Rotation-Invariant Variational Quantum Circuits](https://mlsanity.com/paper/2403.15031/) (2024)
- [Integrating Machine Learning and Quantum Circuits for Proton Affinity Predictions](https://mlsanity.com/paper/2411.17856/) (2024)
- [Quantum Pointwise Convolution: A Flexible and Scalable Approach for Neural Network Enhancement](https://mlsanity.com/paper/2412.01241/) (2024)
- [Quantum continual learning of quantum data realizing knowledge backward transfer](https://mlsanity.com/paper/2203.14032/) (2022)
- [Hacking Cryptographic Protocols with Advanced Variational Quantum Attacks](https://mlsanity.com/paper/2311.02986/) (2023)
- [Guardians of the Quantum GAN](https://mlsanity.com/paper/2404.16156/) (2024)
- [Self-Adaptive Quantum Kernel Principal Components Analysis for Compact Readout of Chemiresistive Sensor Arrays](https://mlsanity.com/paper/2409.00115/) (2024)
- [Quantum Kernel Learning for Small Dataset Modeling in Semiconductor Fabrication: Application to Ohmic Contact](https://mlsanity.com/paper/2409.10803/) (2024)
- [Quantum Machine Learning: An Interplay Between Quantum Computing and Machine Learning](https://mlsanity.com/paper/2411.09403/) (2024)

## Built on by (most cited first, 4 of 4)

- [Machine Unlearning in the Era of Quantum Machine Learning: An Empirical Study](https://mlsanity.com/paper/2512.19253/) (2025)
- [Distribution-Guided and Constrained Quantum Machine Unlearning](https://mlsanity.com/paper/2601.04413/) (2026)
- [Dynamic Entanglement-Weighted Pruning for Quantum Federated Unlearning in Supply-Chain Risk Prediction](https://mlsanity.com/paper/2608.17069/) (2026)
- [Characterizing Privacy Risks of Quantum Machine Learning with Emergent Quantum-Native Access](https://mlsanity.com/paper/2609.05702/) (2026)

## Abstract (arXiv)

Quantum Machine Unlearning has emerged as a foundational challenge at the intersection of quantum information theory privacypreserving computation and trustworthy artificial intelligence This paper advances QMU by establishing a formal framework that unifies physical constraints algorithmic mechanisms and ethical governance within a verifiable paradigm We define forgetting as a contraction of distinguishability between pre and postunlearning models under completely positive trace-preserving dynamics grounding data removal in the physics of quantum irreversibility Building on this foundation we present a fiveaxis taxonomy spanning scope guarantees mechanisms system context and hardware realization linking theoretical constructs to implementable strategies Within this structure we incorporate influence and quantum Fisher information weighted updates parameter reinitialization and kernel alignment as practical mechanisms compatible with noisy intermediatescale quantum NISQ devices The framework extends naturally to federated and privacyaware settings via quantum differential privacy homomorphic encryption and verifiable delegation enabling scalable auditable deletion across distributed quantum systems Beyond technical design we outline a forwardlooking research roadmap emphasizing formal proofs of forgetting scalable and secure architectures postunlearning interpretability and ethically auditable governance Together these contributions elevate QMU from a conceptual notion to a rigorously defined and ethically aligned discipline bridging physical feasibility algorithmic verifiability and societal accountability in the emerging era of quantum intelligence.