Browsing by Author "Zhuang, Jun"

Now showing 1 - 10 of 10
  • Thumbnail Image
    Item
    Anti-perturbation of Online Social Networks by Graph Label Transition
    (arXiv, 2020) Zhuang, Jun; Al Hasan, Mohammad; Computer and Information Science, School of Science
    Online social networks (OSNs) classify users into different categories based on their online activities and interests, a task which is referred as a node classification task. Such a task can be solved effectively using Graph Convolutional Networks (GCNs). However, a small number of users, so-called perturbators, may perform random activities on an OSN, which significantly deteriorate the performance of a GCN-based node classification task. Existing works in this direction defend GCNs either by adversarial training or by identifying the attacker nodes followed by their removal. However, both of these approaches require that the attack patterns or attacker nodes be identified first, which is difficult in the scenario when the number of perturbator nodes is very small. In this work, we develop a GCN defense model, namely GraphLT, which uses the concept of label transition. GraphLT assumes that perturbators' random activities deteriorate GCN's performance. To overcome this issue, GraphLT subsequently uses a novel Bayesian label transition model, which takes GCN's predicted labels and applies label transitions by Gibbs-sampling-based inference and thus repairs GCN's prediction to achieve better node classification. Extensive experiments on seven benchmark datasets show that GraphLT considerably enhances the performance of the node classifier in an unperturbed environment; furthermore, it validates that GraphLT can successfully repair a GCN-based node classifier with superior performance than several competing methods.
  • Thumbnail Image
    Item
    Defending Graph Convolutional Networks against Dynamic Graph Perturbations via Bayesian Self-Supervision
    (AAAI Technical Track, 2022-06-28) Zhuang, Jun; Al Hasan, Mohammad; Computer and Information Science, School of Science
    In recent years, plentiful evidence illustrates that Graph Convolutional Networks (GCNs) achieve extraordinary accomplishments on the node classification task. However, GCNs may be vulnerable to adversarial attacks on label-scarce dynamic graphs. Many existing works aim to strengthen the robustness of GCNs; for instance, adversarial training is used to shield GCNs against malicious perturbations. However, these works fail on dynamic graphs for which label scarcity is a pressing issue. To overcome label scarcity, self-training attempts to iteratively assign pseudo-labels to highly confident unlabeled nodes but such attempts may suffer serious degradation under dynamic graph perturbations. In this paper, we generalize noisy supervision as a kind of self-supervised learning method and then propose a novel Bayesian self-supervision model, namely GraphSS, to address the issue. Extensive experiments demonstrate that GraphSS can not only affirmatively alert the perturbations on dynamic graphs but also effectively recover the prediction of a node classifier when the graph is under such perturbations. These two advantages prove to be generalized over three classic GCNs across five public graph datasets.
  • Thumbnail Image
    Item
    Deperturbation of Online Social Networks via Bayesian Label Transition
    (Society for Industrial and Applied Mathematics, 2022) Zhuang, Jun; Al Hasan, Mohammad; Computer and Information Science, School of Science
    Online social networks (OSNs) classify users into different categories based on their online activities and interests, a task which is referred as a node classification task. Such a task can be solved effectively using Graph Convolutional Networks (GCNs). However, a small number of users, so-called perturbators, may perform random activities on an OSN, which significantly deteriorate the performance of a GCN-based node classification task. Existing works in this direction defend GCNs either by adversarial training or by identifying the attacker nodes followed by their removal. However, both of these approaches require that the attack patterns or attacker nodes be identified first, which is difficult in the scenario when the number of perturbator nodes is very small. In this work, we develop a GCN defense model, namely GraphLT, which uses the concept of label transition. GraphLT assumes that perturbators' random activities deteriorate GCN's performance. To overcome this issue, GraphLT subsequently uses a novel Bayesian label transition model, which takes GCN's predicted labels and applies label transitions by Gibbs-sampling-based inference and thus repairs GCN's prediction to achieve better node classification. Extensive experiments on seven benchmark datasets show that GraphLT considerably enhances the performance of the node classifier in an unperturbed environment; furthermore, it validates that GraphLT can successfully repair a GCN-based node classifier with superior performance than several competing methods.
  • Thumbnail Image
    Item
    Geometrically Matched Multi-source Microscopic Image Synthesis Using Bidirectional Adversarial Networks
    (Springer, 2022) Zhuang, Jun; Wang, Dali; Computer Science, Luddy School of Informatics, Computing, and Engineering
    Microscopic images from multiple modalities can produce plentiful experimental information. In practice, biological or physical constraints under a given observation period may prevent researchers from acquiring enough microscopic scanning. Recent studies demonstrate that image synthesis is one of the popular approaches to release such constraints. Nonetheless, most existing synthesis approaches only translate images from the source domain to the target domain without solid geometric associations. To embrace this challenge, we propose an innovative model architecture, BANIS, to synthesize diversified microscopic images from multi-source domains with distinct geometric features. The experimental outcomes indicate that BANIS successfully synthesizes favorable image pairs on C. elegans microscopy embryonic images. To the best of our knowledge, BANIS is the first application to synthesize microscopic images that associate distinct spatial geometric features from multi-source domains.
  • Thumbnail Image
    Item
    How Does Bayesian Noisy Self-Supervision Defend Graph Convolutional Networks?
    (Springer, 2022-08) Zhuang, Jun; Al Hasan, Mohammad; Computer and Information Science, School of Science
    In recent years, it has been shown that, compared to other contemporary machine learning models, graph convolutional networks (GCNs) achieve superior performance on the node classification task. However, two potential issues threaten the robustness of GCNs, label scarcity and adversarial attacks. .Intensive studies aim to strengthen the robustness of GCNs from three perspectives, the self-supervision-based method, the adversarial-based method, and the detection-based method. Yet, all of the above-mentioned methods can barely handle both issues simultaneously. In this paper, we hypothesize noisy supervision as a kind of self-supervised learning method and then propose a novel Bayesian graph noisy self-supervision model, namely GraphNS, to address both issues. Extensive experiments demonstrate that GraphNS can significantly enhance node classification against both label scarcity and adversarial attacks. This enhancement proves to be generalized over four classic GCNs and is superior to the competing methods across six public graph datasets.
  • Thumbnail Image
    Item
    Improving the Robustness of Artificial Neural Networks via Bayesian Approaches
    (2023-08) Zhuang, Jun; Al Hasan, Mohammad; Mukhopadhyay, Snehasis; Mohler, George; Tuceryan, Mihran
    Artificial neural networks (ANNs) have achieved extraordinary performance in various domains in recent years. However, some studies reveal that ANNs may be vulnerable in three aspects: label scarcity, perturbations, and open-set emerging classes. Noisy labeling and self-supervised learning approaches address the label scarcity issues, but most of the work couldn't handle the perturbations. Adversarial training methods, topological denoising methods, and mechanism designing methods aim to mitigate the negative effects caused by perturbations. However, adversarial training methods can barely train a robust model under the circumstance of extensive label scarcity; topological denoising methods are not efficient on dynamic data structures; and mechanism designing methods often depend on heuristic explorations. Detection-based methods devote to identifying novel or anomaly instances for further downstream tasks. Nonetheless, such instances may belong to open-set new emerging classes. To embrace the aforementioned challenges, we address the robustness issues of ANNs from two aspects. First, we propose a series of Bayesian label transition models to improve the robustness of Graph Neural Networks (GNNs) in the presence of label scarcity and perturbations in the graph domain. Second, we propose a new non-exhaustive learning model, named NE-GM-GAN, to handle both open-set problems and class-imbalance issues in network intrusion datasets. Extensive experiments with several datasets demonstrate that our proposed models can effectively improve the robustness of ANNs.
  • Thumbnail Image
    Item
    Into the Reverie: Exploration of the Dream Market
    (IEEE, 2019-12) Carr, Theo; Zhuang, Jun; Sablan, Dwight; LaRue, Emma; Wu, Yubao; Al Hasan, Mohammad; Mohler, George; Computer and Information Science, School of Science
    Since the emergence of the Silk Road market in the early 2010s, dark web `cryptomarkets' have proliferated and offered people an online platform to buy and sell illicit drugs, relying on cryptocurrencies such as Bitcoin for anonymous transactions. However, recent studies have highlighted the potential for de-anonymization of bitcoin transactions, bringing into question the level of anonymity afforded by cryptomarkets. We examine a set of over 100,000 product reviews from several cryptomarkets collected in 2018 and 2019 and conduct a comprehensive analysis of the markets, including an examination of the distribution of drug sales and revenue among vendors, and a comparison of incidences of opioid sales to overdose deaths in a US city. We explore the potential for de-anonymization of vendors by implementing a Naïve-Bayes classifier to predict the vendor from a given product review, and attempt to link vendors' sales to specific Bitcoin transactions. On the buyer side, we evaluate the efficacy of hierarchical agglomerative clustering for grouping together transactions corresponding to the same buyer. We find that the high degree of specialization among the small subset of high-revenue vendors may render these vendors susceptible to de-anonymization. Further research is necessary to confirm these findings, which are restricted by the scarcity of ground-truth data for validation.
  • Thumbnail Image
    Item
    Lighter U-net for segmenting white matter hyperintensities in MR images
    (ACM, 2019) Zhuang, Jun; Gao, Mingchen; Al Hasan, Mohammad; Computer and Information Science, School of Science
    White matter hyperintensities (WMH) is one of main consequences of small vessel diseases. Automated WMH segmentation techniques play an important role in clinical research and practice. U-Net has been demonstrated to yield the best precise segmentation results so far. However, sometimes it losses more detailed information as network goes deeper. In addition, it usually depends on data augmentation or a large number of filters. Large filters increase the complexity of model, which may be an obstacle for real-time segmentation on cloud computing. To solve these two issues, a new architecture, Lighter U-Net is proposed to reinforce feature use, to reduce the number of parameters as well as to retain sufficient receptive fields without losing resolution. The extensive experiments suggest that the proposed network achieves comparable performance as the state-of-the-art methods by only using 17% parameters of standard U-Net.
  • Thumbnail Image
    Item
    Non-exhaustive Learning Using Gaussian Mixture Generative Adversarial Networks
    (Springer, 2021) Zhuang, Jun; Al Hasan, Mohammad; Computer and Information Science, School of Science
    Supervised learning, while deployed in real-life scenarios, often encounters instances of unknown classes. Conventional algorithms for training a supervised learning model do not provide an option to detect such instances, so they miss-classify such instances with 100% probability. Open Set Recognition (OSR) and Non-Exhaustive Learning (NEL) are potential solutions to overcome this problem. Most existing methods of OSR first classify members of existing classes and then identify instances of new classes. However, many of the existing methods of OSR only makes a binary decision, i.e., they only identify the existence of the unknown class. Hence, such methods cannot distinguish test instances belonging to incremental unseen classes. On the other hand, the majority of NEL methods often make a parametric assumption over the data distribution, which either fail to return good results, due to the reason that real-life complex datasets may not follow a well-known data distribution. In this paper, we propose a new online non-exhaustive learning model, namely, Non-Exhaustive Gaussian Mixture Generative Adversarial Networks (NE-GM-GAN) to address these issues. Our proposed model synthesizes Gaussian mixture based latent representation over a deep generative model, such as GAN, for incremental detection of instances of emerging classes in the test data. Extensive experimental results on several benchmark datasets show that NE-GM-GAN significantly outperforms the state-of-the-art methods in detecting instances of novel classes in streaming data.
  • Thumbnail Image
    Item
    Robust Node Classification on Graphs: Jointly from Bayesian Label Transition and Topology-based Label Propagation
    (ACM, 2022-10-17) Zhuang, Jun; Al Hasan, Mohammad; Computer and Information Science, School of Science
    Node classification using Graph Neural Networks (GNNs) has been widely applied in various real-world scenarios. However, in recent years, compelling evidence emerges that the performance of GNN-based node classification may deteriorate substantially by topological perturbation, such as random connections or adversarial attacks. Various solutions, such as topological denoising methods and mechanism design methods, have been proposed to develop robust GNN-based node classifiers but none of these works can fully address the problems related to topological perturbations. Recently, the Bayesian label transition model is proposed to tackle this issue but its slow convergence may lead to inferior performance. In this work, we propose a new label inference model, namely LInDT, which integrates both Bayesian label transition and topology-based label propagation for improving the robustness of GNNs against topological perturbations. LInDT is superior to existing label transition methods as it improves the label prediction of uncertain nodes by utilizing neighborhood-based label propagation leading to better convergence of label inference. Besides, LIndT adopts asymmetric Dirichlet distribution as a prior, which also helps it to improve label inference. Extensive experiments on five graph datasets demonstrate the superiority of LInDT for GNN-based node classification under three scenarios of topological perturbations.