Journal Articles

Permanent URI for this collectionhttps://mro.massey.ac.nz/handle/10179/7915

Browse

Has files: YesSubject: search.filters.subject.0801 Artificial Intelligence and Image Processing

Search Results

Now showing 1 - 6 of 6
  • Thumbnail Image
    Item
    Masquerade Attacks Against Security Software Exclusion Lists
    (AJIIPS, 2019) McIntosh T; Jang-Jaccard J; Watters P; Susnjak T
    Security software, commonly known as Antivirus, has evolved from simple virus scanners to become multi-functional security suites. To combat ever-growing malware threats, modern security software utilizes both static and dynamic analysis to assess malware threats, inevitably leading to occasional false positive and false negative reports. To mitigate this, existing state-of-the-art security software offers the feature of Exclusion Lists to allow users to exclude specified files and folders from being scanned or monitored. Through rigorous evaluation, however, we found that some of such products stored their Exclusion Lists as unencrypted cleartexts either in known or predictable locations. In this paper we empirically demonstrate how easy it is to exploit the Exclusion Lists by launching masquerade attacks. We argue that the Exclusion Lists should be better implemented such as using application whitelisting, the contents of the lists to be better safeguarded, and only be readable by authorized entities within a strong access control scheme.
  • Thumbnail Image
    Item
    Initialization-similarity clustering algorithm
    (Springer Science+Business Media, LLC, 2019-12) Liu T; Zhu J; Zhou J; Zhu Y; Zhu X
    Classic k-means clustering algorithm randomly selects centroids for initialization to possibly output unstable clustering results. Moreover, random initialization makes the clustering result hard to reproduce. Spectral clustering algorithm is a two-step strategy, which first generates a similarity matrix and then conducts eigenvalue decomposition on the Laplacian matrix of the similarity matrix to obtain the spectral representation. However, the goal of the first step in the spectral clustering algorithm does not guarantee the best clustering result. To address the above issues, this paper proposes an Initialization-Similarity (IS) algorithm which learns the similarity matrix and the new representation in a unified way and fixes initialization using the sum-of-norms regularization to make the clustering more robust. The experimental results on ten real-world benchmark datasets demonstrate that our IS clustering algorithm outperforms the comparison clustering algorithms in terms of three evaluation metrics for clustering algorithm including accuracy (ACC), normalized mutual information (NMI), and Purity.
  • Thumbnail Image
    Item
    Joint Spectral Clustering based on Optimal Graph and Feature Selection
    (Springer Nature Switzerland AG, 2021-02) Zhu J; Jang-Jaccard J; Liu T; Zhou J
    Redundant features and outliers (noise) included in the data points for a machine learning clustering model heavily influences the discovery of more distinguished features for clustering. To solve this issue, we propose a spectral new clustering method to consider the feature selection with the L2 , 1-norm regularization as well as simultaneously learns orthogonal representations for each sample to preserve the local structures of data points. Our model also solves the issue of out-of-sample, where the training process does not output an explicit model to predict unseen data points, along with providing an efficient optimization method for the proposed objective function. Experimental results showed that our method on twelve data sets achieves the best performance compared with other similar models.
  • Thumbnail Image
    Item
    Exploring spiral narratives with immediate feedback in immersive virtual reality serious games for earthquake emergency training
    (1/01/2023) Feng Z; González VA; Mutch C; Amor R; Cabrera-Guerrero G
    Various attempts and approaches have been made to teach individuals about the knowledge of best practice for earthquake emergencies. Among them, Immersive Virtual Reality Serious Games (IVR SGs) have been suggested as an effective tool for emergency training. The notion of IVR SGs is consistent with the concept of problem-based gaming (PBG), where trainees interact with games in a loop of forming a playing strategy, applying the strategy, observing consequences, and making reflection. PBG triggers reflection-on-action, enabling trainees to reform perceptions and establish knowledge after making a response to a scenario. However, in the literature of PBG, little effort has been made for trainees to reflect while they are making a response (i.e., reflection-in-action) in a scenario. In addition, trainees do not have the possibility to adjust their responses and reshape their behaviors according to their reflection-in-action. In order to overcome these limitations, this study proposes a game mechanism, which integrates spiral narratives with immediate feedback, to underpin reflection-in-action and reflective redo in PBG. An IVR SG training system suited to earthquake emergency training was developed, incorporating the proposed game mechanism. A controlled experiment with 99 university students and staff was conducted. Participants were divided into three groups, with three interventions tested: a spiral narrated IVR SG, a linear narrated IVR SG, and a leaflet. Both narrated IVR SGs were effective in terms of immediate knowledge gain and self-efficacy improvement. However, challenges and opportunities for future research have been suggested.
  • Thumbnail Image
    Item
    Parameter-Free Extreme Learning Machine for Imbalanced Classification Authors Li, L - China Agric
    (Springer Science+Business Media, LLC, 2020-12) Li L; Zhao K; Sun R; Gan J; Yuan G; Liu T
    Imbalanced data distribution is a common problem in classification situations, that is the number of samples in different categories varies greatly, thus increasing the classification difficulty. Although many methods have been used for the imbalanced data classification, there are still problems with low classification accuracy in minority class and adding additional parameter settings. In order to increase minority classification accuracy in imbalanced problem, this paper proposes a parameter-free weighting learning mechanism based on extreme learning machine and sample loss values to balance the number of samples in each training step. The proposed method mainly includes two aspects: the sample weight learning process based on the sample losses; the sample selection process and weight update process according to the constraint function and iterations. Experimental results on twelve datasets from the KEEL repository show that the proposed method could achieve more balanced and accurate results than other compared methods in this work.
  • Thumbnail Image
    Item
    Weighted adjacent matrix for K-means clustering
    (Springer Science+Business Media, LLC, 2019-12) Zhou J; Liu T; Zhu J
    K-means clustering is one of the most popular clustering algorithms and has been embedded in other clustering algorithms, e.g. the last step of spectral clustering. In this paper, we propose two techniques to improve previous k-means clustering algorithm by designing two different adjacent matrices. Extensive experiments on public UCI datasets showed the clustering results of our proposed algorithms significantly outperform three classical clustering algorithms in terms of different evaluation metrics.