Sarah Erfani

Sarah Erfani

Auto-generated profile, based on publicly available information

Sarah Erfani

The University of Melbourne

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 September 2023 in IEEE Transactions on Quantum Engineering
Verified
Journal Article
Open access
STShu Lok Tsang
Shu Lok Tsang
MWMaxwell T. West
Maxwell T. West
SESarah M. Erfani
Sarah M. Erfani
Muhammad UsmanMuhammad Usman
Muhammad Usman
Quantum machine learning (QML) has received increasing attention due to its potential to outperform classical machine learning methods in problems such as classification and identification tasks. A subclass of QML methods is quantum generative adversarial networks (QGANs) which have been studied as a quantum counterpart of classical GANs widely used in image manipulation and generation tasks. The existing work on QGANs is still limited to small-scale proof-of-concept examples based on images with significant down-scaling. Here we integrate classical and quantum techniques to propose a new hybrid quantum-classical GAN framework. We demonstrate its superior learning capabilities over existing quantum techniques by generating 28×28 pixels grey-scale images without dimensionality reduction or classical pre/post-processing on multiple classes of the standard MNIST and Fashion MNIST datasets, which achieves comparable results to classical frameworks with three orders of magnitude less trainable generator parameters. To gain further insight into the working of our hybrid approach, we systematically explore the impact of its parameter space by varying the number of qubits, the size of image patches, the number of layers in the generator, the shape of the patches and the choice of prior distribution. Our results show that increasing the quantum generator size generally improves the learning capability of the network. The developed framework provides a foundation for future design of QGANs with optimal parameter set tailored for complex image generation tasks

23 June 2023 in Physical Review Research
Verified
Journal Article
Open access
PDF file
MWMaxwell T. West
Maxwell T. West
SESarah M. Erfani
Sarah M. Erfani
CLChristopher Leckie
Christopher Leckie
MSMartin Sevior
Martin Sevior
LHLloyd C. L. Hollenberg
Lloyd C. L. Hollenberg
Muhammad UsmanMuhammad Usman
Muhammad Usman
Machine learning (ML) methods such as artificial neural networks are rapidly becoming ubiquitous in modern science, technology, and industry. Despite their accuracy and sophistication, neural networks can be easily fooled by carefully designed malicious inputs known as adversarial attacks. While such vulnerabilities remain a serious challenge for classical neural networks, the extent of their existence is not fully understood in the quantum ML setting. In this paper, we benchmark the robustness of quantum ML networks, such as quantum variational classifiers (QVC), at scale by performing rigorous training for both simple and complex image datasets and through a variety of high-end adversarial attacks. Our results show that QVCs offer a notably enhanced robustness against classical adversarial attacks by learning features, which are not detected by the classical neural networks, indicating a possible quantum advantage for ML tasks. Contrarily, and remarkably, the converse is not true, with attacks on quantum networks also capable of deceiving classical neural networks. By combining quantum and classical network outcomes, we propose an adversarial attack detection technology. Traditionally quantum advantage in ML systems has been sought through increased accuracy or algorithmic speed-up, but our study has revealed the potential for a kind of quantum advantage through superior robustness of ML models, whose practical realization will address serious security concerns and reliability issues of ML algorithms employed in a myriad of applications including autonomous vehicles, cybersecurity, and surveillance robotic systems.

26 September 2018
Verified
Book Chapter
Closed access
YHYi Han
Yi Han
BRBenjamin I. P. Rubinstein
Benjamin I. P. Rubinstein
TATamas Abraham
Tamas Abraham
TATansu Alpcan
Tansu Alpcan
OVOlivier De Vel
Olivier De Vel
PMPaul Montague
Paul Montague

11 February 2021 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
SWSandamal Weerasinghe
Sandamal Weerasinghe
TATansu Alpcan
Tansu Alpcan
SESarah M. Erfani
Sarah M. Erfani
CLChristopher Leckie
Christopher Leckie
Support Vector Machines (SVMs) are vulnerable to targeted training data manipulations such as poisoning attacks and label flips. By carefully manipulating a subset of training samples, the attacker forces the learner to compute an incorrect decision boundary, thereby causing misclassifications. Considering the increased importance of SVMs in engineering and life-critical applications, we develop a novel defense algorithm that improves resistance against such attacks. Local Intrinsic Dimensionality (LID) is a promising metric that characterizes the outlierness of data samples. In this work, we introduce a new approximation of LID called K-LID that uses kernel distance in the LID calculation, which allows LID to be calculated in high dimensional transformed spaces. We introduce a weighted SVM against such attacks using K-LID as a distinguishing characteristic that de-emphasizes the effect of suspicious data samples on the SVM decision boundary. Each sample is weighted on how likely its K-LID value is from the benign K-LID distribution rather than the attacked K-LID distribution. Experiments with benchmark data sets show that the proposed defense reduces classification error rates substantially (10% on average).

10 September 2020 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
LALaurent Amsaleg
Laurent Amsaleg
JBJames Bailey
James Bailey
ABAmelie Barbe
Amelie Barbe
SESarah M. Erfani
Sarah M. Erfani
TFTeddy Furon
Teddy Furon
XNXuan Vinh Nguyen
Xuan Vinh Nguyen
Machine learning systems are vulnerable to adversarial attack. By applying to the input object a small, carefullydesigned perturbation, a classifier can be tricked into making an incorrect prediction. This phenomenon has drawn wide interest, with many attempts made to explain it. However, a complete understanding is yet to emerge. In this paper we adopt a slightly different perspective, still relevant to classification. We consider retrieval, where the output is a set of objects most similar to a user-supplied query object, corresponding to the set of k-nearest neighbors. We investigate the effect of adversarial perturbation on the ranking of objects with respect to a query. Through theoretical analysis, supported by experiments, we demonstrate that as the intrinsic dimensionality of the data domain rises, the amount of perturbation required to subvert neighborhood rankings diminishes, and the vulnerability to adversarial attack rises. We examine two modes of perturbation of the query: either ‘closer’ to the target point, or ‘farther’ from it. We also consider two perspectives: ‘query-centric’, examining the effect of perturbation on the query’s own neighborhood ranking, and ‘target-centric’, considering the ranking of the query point in the target’s neighborhood set. All four cases correspond to practical scenarios involving classification and retrieval.

14 August 2019 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
ZGZahra Ghafoori
Zahra Ghafoori
SESarah M. Erfani
Sarah M. Erfani
JBJames C. Bezdek
James C. Bezdek
SKShanika Karunasekera
Shanika Karunasekera
CLChristopher Leckie
Christopher Leckie
We present a new unsupervised dimensionality reduction technique, called LN-SNE, for anomaly detection. LN-SNE generates a parametric embedding by means of Restricted Boltzmann Machines and uses a heavy-tail distribution to project data to a lower dimensional space such that dissimilarities between normal data and anomalies are preserved or strengthened. We compare LN-SNE to several benchmark dimensionality reduction methods on real datasets. The results suggest that LN-SNE for anomaly detection is less sensitive to the dimension of the latent space than the other methods and outperforms them in terms of accuracy. We empirically show that our technique scales near-linearly with respect to the number of dimensions and data size.