Joint Clustering With Correlated Variables

Zhang, Hongmei; Zou, Yubo; Terry, W. Robert; Karmaus, Wilfried; Arshad, Hasan

doi:10.1080/00031305.2018.1424033

Cited by 2 publications

(2 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The high homogeneity can help the clustering model to match each cluster to each type of adversarial example. Therefore, there are several possible ways to improve the multi-label classification performance of the proposed method: (1) Designing a denoising method specialized for the extraction of adversarial perturbation, rather than the simple application of general denoising techniques, i.e., binary filter and median filter; (2) Applying techniques to improve the Homogeneity such as multi-stage clustering [ 32 , 33 ], growing self-organizing maps [ 34 ], and the fractional derivatives [ 35 ]. We will leave those kinds of improvements for future work.…”

Section: Discussionmentioning

confidence: 99%

Clustering Approach for Detecting Multiple Types of Adversarial Examples

Choi

Bahk

Ahn

et al. 2022

Sensors

View full text Add to dashboard Cite

With intentional feature perturbations to a deep learning model, the adversary generates an adversarial example to deceive the deep learning model. As an adversarial example has recently been considered in the most severe problem of deep learning technology, its defense methods have been actively studied. Such effective defense methods against adversarial examples are categorized into one of the three architectures: (1) model retraining architecture; (2) input transformation architecture; and (3) adversarial example detection architecture. Especially, defense methods using adversarial example detection architecture have been actively studied. This is because defense methods using adversarial example detection architecture do not make wrong decisions for the legitimate input data while others do. In this paper, we note that current defense methods using adversarial example detection architecture can classify the input data into only either a legitimate one or an adversarial one. That is, the current defense methods using adversarial example detection architecture can only detect the adversarial examples and cannot classify the input data into multiple classes of data, i.e., legitimate input data and various types of adversarial examples. To classify the input data into multiple classes of data while increasing the accuracy of the clustering model, we propose an advanced defense method using adversarial example detection architecture, which extracts the key features from the input data and feeds the extracted features into a clustering model. From the experimental results under various application datasets, we show that the proposed method can detect the adversarial examples while classifying the types of adversarial examples. We also show that the accuracy of the proposed method outperforms the accuracy of recent defense methods using adversarial example detection architecture.

show abstract

Section: Discussionmentioning

confidence: 99%

Clustering Approach for Detecting Multiple Types of Adversarial Examples

Choi

Bahk

Ahn

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Although it might be beneficial to use oblique rotation, as the lack of correlation between factors, especially those related to quite similar psychological constructs, should not be assumed, an orthogonal (varimax) approach was used instead. The reason behind such a solution was that in the next stage of the procedure obtained factors would be used in cluster analysis, and therefore it would be undesirable if they were not independent (although several solutions for clustering based on correlated variables exist; see, e.g., in [65]). Factors scores were calculated using a method proposed by ten Berge et al [66].…”

Section: Analysis Proceduresmentioning

confidence: 99%

Environmental Attitudes and Willingness to Purchase Online—Classification Approach

Gąsior

2021

Sustainability

View full text Add to dashboard Cite

During the last several years, a tremendous increase in the popularity of online shopping has been observed. There are several possible reasons behind it, some of them, like competitive pricing, convenience or low cost of information search, considered to be extrinsic, others—like ease of use of this channel, pleasure related to it or willingness to reduce social interactions—intrinsic. The purpose of this research is to evaluate another factor, i.e., consumers’ environmental attitudes, in the perspective of their possible relation with the perception and willingness to use online and conventional shopping channels. In order to achieve this, a self-reporting questionnaire was developed and the data from a representative sample of 1000 Polish Internet users was gathered. The research procedure included cluster analysis, whose objective was to identify groups of customers with similar composition of environmental attitudes and next, a set of Kruskal–Wallis tests, aimed at identifying differences in opinions on channels between these clusters. The research proved that large groups of consumers with consistent sets of environmental attitudes exist and the scope of differences between such clusters is not reduced to a unidimensional, “positive–negative” continuum. Furthermore, there are significant differences between clusters in the declared willingness to use online and conventional shopping channels—groups more environmentally-oriented are more willing to purchase online and trust online shops, although they neither perceive conventional retail in a more negative way nor directly prefer online over conventional channels. The nature of such a phenomenon is open to explanation and interpretation, nevertheless, the research proves that environmental attitudes should be included in future models of consumers’ channel choice.

show abstract

Joint Clustering With Correlated Variables

Cited by 2 publications

References 26 publications

Clustering Approach for Detecting Multiple Types of Adversarial Examples

Clustering Approach for Detecting Multiple Types of Adversarial Examples

Environmental Attitudes and Willingness to Purchase Online—Classification Approach

Contact Info

Product

Resources

About