The Quantum Imitation Game: Reverse Engineering of Quantum Machine Learning Models
- URL: http://arxiv.org/abs/2407.07237v2
- Date: Mon, 15 Jul 2024 14:27:14 GMT
- Title: The Quantum Imitation Game: Reverse Engineering of Quantum Machine Learning Models
- Authors: Archisman Ghosh, Swaroop Ghosh,
- Abstract summary: Quantum Machine Learning (QML) amalgamates quantum computing paradigms with machine learning models.
With the expansion of numerous third-party vendors in the Noisy Intermediate-Scale Quantum (NISQ) era of quantum computing, the security of QML models is of prime importance.
We assume the untrusted quantum cloud provider is an adversary having white-box access to the transpiled user-designed trained QML model during inference.
- Score: 2.348041867134616
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Quantum Machine Learning (QML) amalgamates quantum computing paradigms with machine learning models, providing significant prospects for solving complex problems. However, with the expansion of numerous third-party vendors in the Noisy Intermediate-Scale Quantum (NISQ) era of quantum computing, the security of QML models is of prime importance, particularly against reverse engineering, which could expose trained parameters and algorithms of the models. We assume the untrusted quantum cloud provider is an adversary having white-box access to the transpiled user-designed trained QML model during inference. Reverse engineering (RE) to extract the pre-transpiled QML circuit will enable re-transpilation and usage of the model for various hardware with completely different native gate sets and even different qubit technology. Such flexibility may not be obtained from the transpiled circuit which is tied to a particular hardware and qubit technology. The information about the number of parameters, and optimized values can allow further training of the QML model to alter the QML model, tamper with the watermark, and/or embed their own watermark or refine the model for other purposes. In this first effort to investigate the RE of QML circuits, we perform RE and compare the training accuracy of original and reverse-engineered Quantum Neural Networks (QNNs) of various sizes. We note that multi-qubit classifiers can be reverse-engineered under specific conditions with a mean error of order 1e-2 in a reasonable time. We also propose adding dummy fixed parametric gates in the QML models to increase the RE overhead for defense. For instance, adding 2 dummy qubits and 2 layers increases the overhead by ~1.76 times for a classifier with 2 qubits and 3 layers with a performance overhead of less than 9%. We note that RE is a very powerful attack model which warrants further efforts on defenses.
Related papers
- QuantumSEA: In-Time Sparse Exploration for Noise Adaptive Quantum
Circuits [82.50620782471485]
QuantumSEA is an in-time sparse exploration for noise-adaptive quantum circuits.
It aims to achieve two key objectives: (1) implicit circuits capacity during training and (2) noise robustness.
Our method establishes state-of-the-art results with only half the number of quantum gates and 2x time saving of circuit executions.
arXiv Detail & Related papers (2024-01-10T22:33:00Z) - Classical-to-Quantum Transfer Learning Facilitates Machine Learning with Variational Quantum Circuit [62.55763504085508]
We prove that a classical-to-quantum transfer learning architecture using a Variational Quantum Circuit (VQC) improves the representation and generalization (estimation error) capabilities of the VQC model.
We show that the architecture of classical-to-quantum transfer learning leverages pre-trained classical generative AI models, making it easier to find the optimal parameters for the VQC in the training stage.
arXiv Detail & Related papers (2023-05-18T03:08:18Z) - QuMoS: A Framework for Preserving Security of Quantum Machine Learning
Model [10.543277412560233]
Security has always been a critical issue in machine learning (ML) applications.
Model-stealing attack is one of the most fundamental but vitally important issues.
We propose a novel framework, namely QuMoS, to preserve model security.
arXiv Detail & Related papers (2023-04-23T01:17:43Z) - Quantum Imitation Learning [74.15588381240795]
We propose quantum imitation learning (QIL) with a hope to utilize quantum advantage to speed up IL.
We develop two QIL algorithms, quantum behavioural cloning (Q-BC) and quantum generative adversarial imitation learning (Q-GAIL)
Experiment results demonstrate that both Q-BC and Q-GAIL can achieve comparable performance compared to classical counterparts.
arXiv Detail & Related papers (2023-04-04T12:47:35Z) - QSAN: A Near-term Achievable Quantum Self-Attention Network [73.15524926159702]
Self-Attention Mechanism (SAM) is good at capturing the internal connections of features.
A novel Quantum Self-Attention Network (QSAN) is proposed for image classification tasks on near-term quantum devices.
arXiv Detail & Related papers (2022-07-14T12:22:51Z) - Study of Feature Importance for Quantum Machine Learning Models [0.0]
Predictor importance is a crucial part of data preprocessing pipelines in classical and quantum machine learning (QML)
This work presents the first study of its kind in which feature importance for QML models has been explored and contrasted against their classical machine learning (CML) equivalents.
We developed a hybrid quantum-classical architecture where QML models are trained and feature importance values are calculated from classical algorithms on a real-world dataset.
arXiv Detail & Related papers (2022-02-18T15:21:47Z) - Structural risk minimization for quantum linear classifiers [0.0]
Quantum machine learning (QML) stands out as one of the typically highlighted candidates for quantum computing's near-term "killer application"
We investigate capacity measures of two closely related QML models called explicit and implicit quantum linear classifiers.
We identify that the rank and Frobenius norm of the observables used in the QML model closely control the model's capacity.
arXiv Detail & Related papers (2021-05-12T10:39:55Z) - Hybrid quantum-classical classifier based on tensor network and
variational quantum circuit [0.0]
We introduce a hybrid model combining the quantum-inspired tensor networks (TN) and the variational quantum circuits (VQC) to perform supervised learning tasks.
We show that a matrix product state based TN with low bond dimensions performs better than PCA as a feature extractor to compress data for the input of VQCs in the binary classification of MNIST dataset.
arXiv Detail & Related papers (2020-11-30T09:43:59Z) - Once Quantization-Aware Training: High Performance Extremely Low-bit
Architecture Search [112.05977301976613]
We propose to combine Network Architecture Search methods with quantization to enjoy the merits of the two sides.
We first propose the joint training of architecture and quantization with a shared step size to acquire a large number of quantized models.
Then a bit-inheritance scheme is introduced to transfer the quantized models to the lower bit, which further reduces the time cost and improves the quantization accuracy.
arXiv Detail & Related papers (2020-10-09T03:52:16Z) - On the learnability of quantum neural networks [132.1981461292324]
We consider the learnability of the quantum neural network (QNN) built on the variational hybrid quantum-classical scheme.
We show that if a concept can be efficiently learned by QNN, then it can also be effectively learned by QNN even with gate noise.
arXiv Detail & Related papers (2020-07-24T06:34:34Z) - Supervised Learning Using a Dressed Quantum Network with "Super
Compressed Encoding": Algorithm and Quantum-Hardware-Based Implementation [7.599675376503671]
Implementation of variational Quantum Machine Learning (QML) algorithms on Noisy Intermediate-Scale Quantum (NISQ) devices has issues related to the high number of qubits needed and the noise associated with multi-qubit gates.
We propose a variational QML algorithm using a dressed quantum network to address these issues.
Unlike in most other existing QML algorithms, our quantum circuit consists only of single-qubit gates, making it robust against noise.
arXiv Detail & Related papers (2020-07-20T16:29:32Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.