QuanTest: Entanglement-Guided Testing of Quantum Neural Network Systems
- URL: http://arxiv.org/abs/2402.12950v1
- Date: Tue, 20 Feb 2024 12:11:28 GMT
- Title: QuanTest: Entanglement-Guided Testing of Quantum Neural Network Systems
- Authors: Jinjing Shi, Zimeng Xiao, Heyuan Shi, Yu Jiang, Xuelong Li
- Abstract summary: Quantum Neural Network (QNN) combines the Deep Learning (DL) principle with the fundamental theory of quantum mechanics to achieve machine learning tasks with quantum acceleration.
QNN systems differ significantly from traditional quantum software and classical DL systems, posing critical challenges for QNN testing.
We propose QuanTest, a quantum entanglement-guided adversarial testing framework to uncover potential erroneous behaviors in QNN systems.
- Score: 48.476022756096185
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Quantum Neural Network (QNN) combines the Deep Learning (DL) principle with
the fundamental theory of quantum mechanics to achieve machine learning tasks
with quantum acceleration. Recently, QNN systems have been found to manifest
robustness issues similar to classical DL systems. There is an urgent need for
ways to test their correctness and security. However, QNN systems differ
significantly from traditional quantum software and classical DL systems,
posing critical challenges for QNN testing. These challenges include the
inapplicability of traditional quantum software testing methods, the dependence
of quantum test sample generation on perturbation operators, and the absence of
effective information in quantum neurons. In this paper, we propose QuanTest, a
quantum entanglement-guided adversarial testing framework to uncover potential
erroneous behaviors in QNN systems. We design a quantum entanglement adequacy
criterion to quantify the entanglement acquired by the input quantum states
from the QNN system, along with two similarity metrics to measure the proximity
of generated quantum adversarial examples to the original inputs. Subsequently,
QuanTest formulates the problem of generating test inputs that maximize the
quantum entanglement sufficiency and capture incorrect behaviors of the QNN
system as a joint optimization problem and solves it in a gradient-based manner
to generate quantum adversarial examples. Experimental results demonstrate that
QuanTest possesses the capability to capture erroneous behaviors in QNN systems
(generating 67.48%-96.05% more test samples than the random noise under the
same perturbation size constraints). The entanglement-guided approach proves
effective in adversarial testing, generating more adversarial examples (maximum
increase reached 21.32%).
Related papers
- 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) - Quantum-Error-Mitigation Circuit Groups for Noisy Quantum Metrology [0.0]
Quantum technologies work by utilizing properties inherent in quantum systems such as quantum coherence and quantum entanglement.
Quantum technologies are fragile against an interaction with an environment (decoherence) and in order to utilize them with high accuracy we need to develop error mitigation techniques.
arXiv Detail & Related papers (2023-03-03T10:01:42Z) - QuanGCN: Noise-Adaptive Training for Robust Quantum Graph Convolutional
Networks [124.7972093110732]
We propose quantum graph convolutional networks (QuanGCN), which learns the local message passing among nodes with the sequence of crossing-gate quantum operations.
To mitigate the inherent noises from modern quantum devices, we apply sparse constraint to sparsify the nodes' connections.
Our QuanGCN is functionally comparable or even superior than the classical algorithms on several benchmark graph datasets.
arXiv Detail & Related papers (2022-11-09T21:43:16Z) - Experimental Implementation of an Efficient Test of Quantumness [49.588006756321704]
A test of quantumness is a protocol where a classical user issues challenges to a quantum device to determine if it exhibits non-classical behavior.
Recent attempts to implement such tests on current quantum computers rely on either interactive challenges with efficient verification, or non-interactive challenges with inefficient (exponential time) verification.
arXiv Detail & Related papers (2022-09-28T18:00:04Z) - Evaluating the performance of sigmoid quantum perceptrons in quantum
neural networks [0.0]
Quantum neural networks (QNN) have been proposed as a promising architecture for quantum machine learning.
One candidate is quantum perceptrons designed to emulate the nonlinear activation functions of classical perceptrons.
We critically investigate both the capabilities and performance of SQP networks by computing their effective dimension and effective capacity.
arXiv Detail & Related papers (2022-08-12T10:08:11Z) - Entanglement entropy production in Quantum Neural Networks [0.0]
Quantum Neural Networks (QNN) are considered a candidate for achieving quantum advantage in the Noisy Intermediate Quantum computer (NISQ) era.
We show a universal behavior for the rate at which entanglement is created in any given QNN architecture.
We introduce new measure to characterize the entanglement production in QNNs: the entangling speed.
arXiv Detail & Related papers (2022-06-06T10:17:17Z) - Quantum Federated Learning with Quantum Data [87.49715898878858]
Quantum machine learning (QML) has emerged as a promising field that leans on the developments in quantum computing to explore large complex machine learning problems.
This paper proposes the first fully quantum federated learning framework that can operate over quantum data and, thus, share the learning of quantum circuit parameters in a decentralized manner.
arXiv Detail & Related papers (2021-05-30T12:19:27Z) - 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)
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.