Jun Zhuang

Jun Zhuang, Mohammad Al Hasan

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.

Jun Zhuang, Mohammad Al Hasan

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.

Caleb Geren, Amanda Board, Gaby G. Dagher et al.

With the growing development and deployment of large language models (LLMs) in both industrial and academic fields, their security and safety concerns have become increasingly critical. However, recent studies indicate that LLMs face numerous vulnerabilities, including data poisoning, prompt injections, and unauthorized data exposure, which conventional methods have struggled to address fully. In parallel, blockchain technology, known for its data immutability and decentralized structure, offers a promising foundation for safeguarding LLMs. In this survey, we aim to comprehensively assess how to leverage blockchain technology to enhance LLMs' security and safety. Besides, we propose a new taxonomy of blockchain for large language models (BC4LLMs) to systematically categorize related works in this emerging field. Our analysis includes novel frameworks and definitions to delineate security and safety in the context of BC4LLMs, highlighting potential research directions and challenges at this intersection. Through this study, we aim to stimulate targeted advancements in blockchain-integrated LLM security.

Jun Zhuang, Mohammad Al Hasan

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.

Jun Zhuang, Dali Wang

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.