Robustness Verification of Quantum Classifiers

Guan, Ji; Wang, Fang; Ying, Mingsheng

doi:10.1007/978-3-030-81685-8_7

Cited by 15 publications

(12 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, we prove the robustness of the QAML model based on the ϵrobust accuracy proposed in Ref. [27]. Given a test sample set S and a smaller threshold ϵ.…”

Section: Numerical Simulations and Discussionmentioning

confidence: 71%

Quantum adversarial metric learning model based on triplet loss function

Hou

Chen

et al. 2022

Preprint

View full text Add to dashboard Cite

Metric learning plays an essential role in image analysis and classification, and it has attracted more and more attention. In this paper, we propose a quantum adversarial metric learning (QAML) model based on the triplet loss function, where samples are embedded into the high-dimensional Hilbert space and the optimal metric is obtained by minimizing the triplet loss function. The QAML model employs entanglement and interference to build superposition states for triplet samples so that only one parameterized quantum circuit is needed to calculate sample distances, which reduces the demand for quantum resources. Considering the QAML model is fragile to adversarial attacks, an adversarial sample generation strategy is designed based on the quantum gradient ascent method, effectively improving the robustness against the functional adversarial attack. Simulation results show that the QAML model can effectively distinguish samples of MNIST and Iris datasets and has higher robustness over the general quantum metric learning. The QAML model is a fundamental research problem of machine learning. As a subroutine of classification and clustering tasks, the QAML model opens an avenue for exploring quantum advantages in machine learning.

show abstract

“…Furthermore, we prove the robustness of the QAML model based on the ϵrobust accuracy proposed in Ref. [27]. Given a test sample set S and a smaller threshold ϵ.…”

Section: Numerical Simulations and Discussionmentioning

confidence: 71%

Quantum adversarial metric learning model based on triplet loss function

Hou

Chen

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In particular, its efficiency is shown by a class of random quantum decision models with 27 qubits, which works on a 2 27 -dimensional state space. The state-of-the-art verification algorithm [26] for quantum machine learning was only able to deal with (the robustness with) 9 qubits. Our experiments can be considered a big step toward the demanded number (≥50) of qubits in practical applications of the NISQ era.…”

Section: Contributions Of This Papermentioning

confidence: 99%

“…In the last few years, quite a few papers have been devoted to (adversarial) robustness verification of quantum machine learning (e.g. [26][27][28]), where a verifier is given a nominal input quantum datum and it checks robustness in a neighborhood of that particular input datum. However, the techniques developed in these works cannot be directly generalized to solve our problem of fairness verification, because we are required to check a global property.…”

Section: Related Work and Challengesmentioning

confidence: 99%

See 1 more Smart Citation

Verifying Fairness in Quantum Machine Learning

Guan

Wang

Ying

2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Due to the beyond-classical capability of quantum computing, quantum machine learning is applied independently or embedded in classical models for decision making, especially in the field of finance. Fairness and other ethical issues are often one of the main concerns in decision making. In this work, we define a formal framework for the fairness verification and analysis of quantum machine learning decision models, where we adopt one of the most popular notions of fairness in the literature based on the intuition—any two similar individuals must be treated similarly and are thus unbiased. We show that quantum noise can improve fairness and develop an algorithm to check whether a (noisy) quantum machine learning model is fair. In particular, this algorithm can find bias kernels of quantum data (encoding individuals) during checking. These bias kernels generate infinitely many bias pairs for investigating the unfairness of the model. Our algorithm is designed based on a highly efficient data structure—Tensor Networks—and implemented on Google’s TensorFlow Quantum. The utility and effectiveness of our algorithm are confirmed by the experimental results, including income prediction and credit scoring on real-world data, for a class of random (noisy) quantum decision models with 27 qubits ($$2^{27}$$227-dimensional state space) tripling ($$2^{18}$$218times more than) that of the state-of-the-art algorithms for verifying quantum machine learning models.

show abstract

“…The experiments of[26] were performed on a personal computer and the size is at most 8 qubits. We have estimated and tested the same experiments on the server we used in this paper and only 9 qubits can be handled.…”

mentioning

confidence: 99%

Verifying Fairness in Quantum Machine Learning

Guan¹,

Wang²,

Ying³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Due to the beyond-classical capability of quantum computing, quantum machine learning is applied independently or embedded in classical models for decision making, especially in the field of finance. Fairness and other ethical issues are often one of the main concerns in decision making. In this work, we define a formal framework for the fairness verification and analysis of quantum machine learning decision models, where we adopt one of the most popular notions of fairness in the literature based on the intuition -any two similar individuals must be treated similarly and are thus unbiased. We show that quantum noise can improve fairness and develop an algorithm to check whether a (noisy) quantum machine learning model is fair. In particular, this algorithm can find bias kernels of quantum data (encoding individuals) during checking. These bias kernels generate infinitely many bias pairs for investigating the unfairness of the model. Our algorithm is designed based on a highly efficient data structure -Tensor Networks -and implemented on Google's TensorFlow Quantum. The utility and effectiveness of our algorithm are confirmed by the experimental results, including income prediction and credit scoring on real-world data, for a class of random (noisy) quantum decision models with 27 qubits (2 27 -dimensional state space) tripling (2 18 times more than) that of the state-of-the-art algorithms for verifying quantum machine learning models.

show abstract

Robustness Verification of Quantum Classifiers

Cited by 15 publications

References 30 publications

Quantum adversarial metric learning model based on triplet loss function

Quantum adversarial metric learning model based on triplet loss function

Verifying Fairness in Quantum Machine Learning

Verifying Fairness in Quantum Machine Learning

Contact Info

Product

Resources

About