Paul Miller
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Paul Miller has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Barry Devereux
Queen's University Belfast
2 shared publications - Jesus Martinez del Rincon
Centre for Secure Information Technologies (CSIT), Queen’s University Belfast, Belfast, United Kingdom of Great Britain and Northern Ireland
2 shared publications - Niall McLaughlin
Centre for Secure Information Technologies (CSIT), Queen’s University Belfast, Belfast, United Kingdom of Great Britain and Northern Ireland
2 shared publications - Steven Derby
Queen's University Belfast Belfast United Kingdom
2 shared publications - Brian Murphy
Queen's University Belfast Belfast United Kingdom
1 shared publication - Danny Crookes
School of Electronics, Electrical Engineering and Computer Science, Queens University Belfast, Belfast, U.K.
1 shared publication
Latest Publications
- Open Access
Hard-label based Small Query Black-box Adversarial Attack
We consider the hard label based black box adversarial attack setting which solely observes predicted classes from the target model. Most of the attack methods in this setting suffer from impractical number of queries required to achieve a successful attack. One approach to tackle this drawback is utilising the adversarial transferability between white box surrogate models and black box target model. However, the majority of the methods adopting this approach are soft label based to take the full advantage of zeroth order optimisation. Unlike mainstream methods, we propose a new practical setting of hard label based attack with an optimisation process guided by a pretrained surrogate model. Experiments show the proposed method significantly improves the query efficiency of the hard label based black-box attack across various target model architectures. We find the proposed method achieves approximately 5 times higher attack success rate compared to the benchmarks, especially at the small query budgets as 100 and 250.
Open AccessHard-label based Small Query Black-box Adversarial Attack
We consider the hard label based black box adversarial attack setting which solely observes predicted classes from the target model. Most of the attack methods in this setting suffer from impractical number of queries required to achieve a successful attack. One approach to tackle this drawback is utilising the adversarial transferability between white box surrogate models and black box target model. However, the majority of the methods adopting this approach are soft label based to take the full advantage of zeroth order optimisation. Unlike mainstream methods, we propose a new practical setting of hard label based attack with an optimisation process guided by a pretrained surrogate model. Experiments show the proposed method significantly improves the query efficiency of the hard label based black-box attack across various target model architectures. We find the proposed method achieves approximately 5 times higher attack success rate compared to the benchmarks, especially at the small query budgets as 100 and 250.
- Open Access
Feature2Vec: Distributional semantic modelling of human property knowledge
Feature norm datasets of human conceptual knowledge, collected in surveys of human volunteers, yield highly interpretable models of word meaning and play an important role in neurolinguistic research on semantic cognition. However, these datasets are limited in size due to practical obstacles associated with exhaustively listing properties for a large number of words. In contrast, the development of distributional modelling techniques and the availability of vast text corpora have allowed researchers to construct effective vector space models of word meaning over large lexicons. However, this comes at the cost of interpretable, human-like information about word meaning. We propose a method for mapping human property knowledge onto a distributional semantic space, which adapts the word2vec architecture to the task of modelling concept features. Our approach gives a measure of concept and feature affinity in a single semantic space, which makes for easy and efficient ranking of candidate human-derived semantic properties for arbitrary words. We compare our model with a previous approach, and show that it performs better on several evaluation tasks. Finally, we discuss how our method could be used to develop efficient sampling techniques to extend existing feature norm datasets in a reliable way.
Open AccessFeature2Vec: Distributional semantic modelling of human property knowledge
Feature norm datasets of human conceptual knowledge, collected in surveys of human volunteers, yield highly interpretable models of word meaning and play an important role in neurolinguistic research on semantic cognition. However, these datasets are limited in size due to practical obstacles associated with exhaustively listing properties for a large number of words. In contrast, the development of distributional modelling techniques and the availability of vast text corpora have allowed researchers to construct effective vector space models of word meaning over large lexicons. However, this comes at the cost of interpretable, human-like information about word meaning. We propose a method for mapping human property knowledge onto a distributional semantic space, which adapts the word2vec architecture to the task of modelling concept features. Our approach gives a measure of concept and feature affinity in a single semantic space, which makes for easy and efficient ranking of candidate human-derived semantic properties for arbitrary words. We compare our model with a previous approach, and show that it performs better on several evaluation tasks. Finally, we discuss how our method could be used to develop efficient sampling techniques to extend existing feature norm datasets in a reliable way.
- 22 August 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. PP (10414347) , 1
Component-based Feature Saliency for Clustering
Simultaneous feature selection and clustering is a major challenge in unsupervised learning. In particular, there has been significant research into saliency measures for features that result in good clustering. However, as datasets become larger and more complex, there is a need to adopt a finer-grained approach to saliency by measuring it in relation to a part of a model. Another issue is learning the feature saliency and advanced model parameters. We address the first by presenting a novel Gaussian mixture model, which explicitly models the dependency of individual mixture components on each feature giving a new component-based feature saliency measure. For the second, we use Markov Chain Monte Carlo sampling to estimate the model and hidden variables. Using a synthetic dataset, we demonstrate the superiority of our approach, in terms of clustering accuracy and model parameter estimation, over an approach using a model-based feature saliency with expectation maximisation. We performed an evaluation of our approach with six synthetic trajectory datasets. To demonstrate the generality of our approach, we applied it to a network traffic flow dataset for intrusion detection. Finally, we performed a comparison with state-of-the-art clustering techniques using three real-world trajectory datasets of vehicle traffic.
- 22 August 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. PP (10414347) , 1
Component-based Feature Saliency for Clustering
Simultaneous feature selection and clustering is a major challenge in unsupervised learning. In particular, there has been significant research into saliency measures for features that result in good clustering. However, as datasets become larger and more complex, there is a need to adopt a finer-grained approach to saliency by measuring it in relation to a part of a model. Another issue is learning the feature saliency and advanced model parameters. We address the first by presenting a novel Gaussian mixture model, which explicitly models the dependency of individual mixture components on each feature giving a new component-based feature saliency measure. For the second, we use Markov Chain Monte Carlo sampling to estimate the model and hidden variables. Using a synthetic dataset, we demonstrate the superiority of our approach, in terms of clustering accuracy and model parameter estimation, over an approach using a model-based feature saliency with expectation maximisation. We performed an evaluation of our approach with six synthetic trajectory datasets. To demonstrate the generality of our approach, we applied it to a network traffic flow dataset for intrusion detection. Finally, we performed a comparison with state-of-the-art clustering techniques using three real-world trajectory datasets of vehicle traffic.
- Open Access
Using Sparse Semantic Embeddings Learned from Multimodal Text and Image Data to Model Human Conceptual Knowledge
Distributional models provide a convenient way to model semantics using dense embedding spaces derived from unsupervised learning algorithms. However, the dimensions of dense embedding spaces are not designed to resemble human semantic knowledge. Moreover, embeddings are often built from a single source of information (typically text data), even though neurocognitive research suggests that semantics is deeply linked to both language and perception. In this paper, we combine multimodal information from both text and image-based representations derived from state-of-the-art distributional models to produce sparse, interpretable vectors using Joint Non-Negative Sparse Embedding. Through in-depth analyses comparing these sparse models to human-derived behavioural and neuroimaging data, we demonstrate their ability to predict interpretable linguistic descriptions of human ground-truth semantic knowledge.
Open AccessUsing Sparse Semantic Embeddings Learned from Multimodal Text and Image Data to Model Human Conceptual Knowledge
Distributional models provide a convenient way to model semantics using dense embedding spaces derived from unsupervised learning algorithms. However, the dimensions of dense embedding spaces are not designed to resemble human semantic knowledge. Moreover, embeddings are often built from a single source of information (typically text data), even though neurocognitive research suggests that semantics is deeply linked to both language and perception. In this paper, we combine multimodal information from both text and image-based representations derived from state-of-the-art distributional models to produce sparse, interpretable vectors using Joint Non-Negative Sparse Embedding. Through in-depth analyses comparing these sparse models to human-derived behavioural and neuroimaging data, we demonstrate their ability to predict interpretable linguistic descriptions of human ground-truth semantic knowledge.
- Open Access
- 8 December 2015
- Published by MDPI AG in Algorithms
- Vol. 8 (4) , 1143-1174
Generating Realistic Labelled, Weighted Random Graphs
Generative algorithms for random graphs have yielded insights into the structure and evolution of real-world networks. Most networks exhibit a well-known set of properties, such as heavy-tailed degree distributions, clustering and community formation. Usually, random graph models consider only structural information, but many real-world networks also have labelled vertices and weighted edges. In this paper, we present a generative model for random graphs with discrete vertex labels and numeric edge weights. The weights are represented as a set of Beta Mixture Models (BMMs) with an arbitrary number of mixtures, which are learned from real-world networks. We propose a Bayesian Variational Inference (VI) approach, which yields an accurate estimation while keeping computation times tractable. We compare our approach to state-of-the-art random labelled graph generators and an earlier approach based on Gaussian Mixture Models (GMMs). Our results allow us to draw conclusions about the contribution of vertex labels and edge weights to graph structure.
- 8 December 2015
- Published by MDPI AG in Algorithms
- Vol. 8 (4) , 1143-1174
Open AccessGenerating Realistic Labelled, Weighted Random Graphs
Generative algorithms for random graphs have yielded insights into the structure and evolution of real-world networks. Most networks exhibit a well-known set of properties, such as heavy-tailed degree distributions, clustering and community formation. Usually, random graph models consider only structural information, but many real-world networks also have labelled vertices and weighted edges. In this paper, we present a generative model for random graphs with discrete vertex labels and numeric edge weights. The weights are represented as a set of Beta Mixture Models (BMMs) with an arbitrary number of mixtures, which are learned from real-world networks. We propose a Bayesian Variational Inference (VI) approach, which yields an accurate estimation while keeping computation times tractable. We compare our approach to state-of-the-art random labelled graph generators and an earlier approach based on Gaussian Mixture Models (GMMs). Our results allow us to draw conclusions about the contribution of vertex labels and edge weights to graph structure.
- 30 August 2007
- Published by Optica Publishing Group in Applied Optics
- Vol. 46 (25) , 6405-6418
Signal-to-noise-ratio analysis for nonlinear N-ary phase filters
The problem of recognizing targets in nonoverlapping clutter using nonlinear N-ary phase filters is addressed. Using mathematical analysis, expressions were derived for an N-ary phase filter and the intensity variance of an optical correlator output. The N-ary phase filter was shown to consist of an infinite sum of harmonic terms whose periodicity was determined by N. For the intensity variance, it was found that under certain conditions the variance was minimized due to a previously undiscovered phase quadrature effect. Comparison showed that optimal real filters produced greater signal-to-noise-ratio values than the continuous phase versions as a consequence of this effect.
- 30 August 2007
- Published by Optica Publishing Group in Applied Optics
- Vol. 46 (25) , 6405-6418
Signal-to-noise-ratio analysis for nonlinear N-ary phase filters
The problem of recognizing targets in nonoverlapping clutter using nonlinear N-ary phase filters is addressed. Using mathematical analysis, expressions were derived for an N-ary phase filter and the intensity variance of an optical correlator output. The N-ary phase filter was shown to consist of an infinite sum of harmonic terms whose periodicity was determined by N. For the intensity variance, it was found that under certain conditions the variance was minimized due to a previously undiscovered phase quadrature effect. Comparison showed that optimal real filters produced greater signal-to-noise-ratio values than the continuous phase versions as a consequence of this effect.