Spear and Shield: Adversarial Attacks and Defense Methods for Model-Based Link Prediction on Continuous-Time Dynamic Graphs

The adversarial attack is a cutting-edge technique used to study the vulnerability of deep neural networks (DNNs). However, most existing studies focus on the additive perturbation-based attack, which cannot represent real-world corruption and limit their applications. In particular, haze is a common natural phenomenon that significantly corrupts an image, which inevitably poses a potential threat to deep models. In this work, for the first attempt, we study the effects of haze on DNNs from the perspective of adversarial attacks and propose two adversarial haze attack methods. We first propose the optimization-based adversarial haze attack (OAdvHaze) that optimizes the parameters of the atmospheric scattering model with the guidance of a DNN to synthesize a hazy image, which leads to a high attack success rate. To achieve a more efficient attack, we further propose a predictive adversarial haze attack (PAdvHaze) employing a DNN to predict the hazing parameters through a one-step way. To validate the effectiveness of both methods, we conducted extensive experiments on two publicly available datasets, i.e., ILSVRC 2012 and NIPS 2017. OAdvHaze and PAdvHaze achieve comparable attack success rates and transferability to state-of-the-art attacks. This work would contribute to the evaluation and enhancement of the robustness of DNNs against haze perturbation that may happen in the real world.

Link prediction based on bipartite networks can not only mine hidden relationships between different types of nodes, but also reveal the inherent law of network evolution. Existing bipartite network link prediction is mainly based on the global structure that cannot analyze the role of the local structure in link prediction. To tackle this problem, this paper proposes a deep link-prediction (DLP) method by leveraging the local structure of bipartite networks. The method first extracts the local structure between target nodes and observes structural information between nodes from a local perspective. Then, representation learning of the local structure is performed on the basis of the graph neural network to extract latent features between target nodes. Lastly, a deep-link prediction model is trained on the basis of latent features between target nodes to achieve link prediction. Experimental results on five datasets showed that DLP achieved significant improvement over existing state-of-the-art link prediction methods. In addition, this paper analyzes the relationship between local structure and link prediction, confirming the effectiveness of a local structure in link prediction.

In recent years, network embedding has attracted much attention from researchers and achieved excellent performance. But few works investigate the adaptability of network embedding, especially for performance in different network structures. Heterogeneity, as a universal topological characteristic, plays a prominent role in network behaviors. In this study, we investigate the effect of heterogeneity on the effectiveness of existing network embedding approaches. We conduct experiments in scale-free networks with varying power exponents from both macro and micro perspectives to address link prediction and node similarity tasks, respectively. The results indicate that network embedding approaches can be divided into two classes according to their performance in the link prediction task. As the network heterogeneity decreases, the performance of approaches in the first class declines, while the performance of approaches in the second class initially improves and then declines. Moreover, our simulation discovers that, based on the node similarity metric, nodes are partitioned into two clusters by approaches, corresponding to large-degree nodes and small-degree nodes, respectively. Furthermore, approaches in the same class present similar characteristics between large-degree nodes and small-degree nodes, and the embedding is interpreted to some extent. Performance variations in the link prediction task can be explained by the characteristics of approaches, and similar characteristics are confirmed in experiments on real networks. Based on the findings for link prediction, we offer a brief guide for choosing an appropriate method based on the extent of heterogeneity. The investigation provides insight into network embedding and offers some interpretation of embedding.

Link prediction is a common problem in network science that cuts across many disciplines. The goal is to forecast the appearance of new links or to find links missing in the network. Typical methods for link prediction use the topology of the network to predict the most likely future or missing connections between a pair of nodes. However, network evolution is often mediated by higher-order structures involving more than pairs of nodes; for example, cliques on three nodes (also called triangles) are key to the structure of social networks, but the standard link prediction framework does not directly predict these structures. To address this gap, in recent work, we propose a new link prediction task called “pairwise link prediction” that directly targets the prediction of new triangles, where one is tasked with finding which nodes are most likely to form a triangle with a given edge. We extend this work in this manuscript, and we evaluate a variety of natural extensions to link prediction methods including neighborhood and PageRank-based methods. A key difference from our previous work is the definition of the neighborhood of an edge, which has a surprisingly large impact on the empirical performance. Our experiments on a variety of networks show that diffusion-based methods are less sensitive to the type of graphs used and more consistent in their results. We also show how our pairwise link prediction framework can be used to get better predictions within the context of standard link prediction evaluation.

Link prediction is one of the fundamental problems for graph-structured data. However, a number of applications of link prediction, such as predicting commercial ties or memberships within a criminal organization, are adversarial, with another party aiming to minimize its effectiveness by manipulating observed information about the graph. In this paper, we focus on the feasibility of mounting adversarial attacks against link prediction algorithms based on graph neural networks. We first propose a greedy heuristic that exploits incremental computation to find attacks against a state-of-the-art link prediction algorithm, called SEAL. We then design an efficient variant of this algorithm that incorporates the link formation mechanism and Υ-decaying heuristic theory to design more effective adversarial attacks. We used real-world datasets and performed an extensive array of experiments to show that the performance of SEAL is negatively affected by a significant margin. More importantly, our experimental results have shown that our adversarial attacks mounted based on SEAL can be readily transferred to several existing link prediction heuristics in the literature.

Improving local clustering based top-L link prediction methods via asymmetric link clustering information

Recently, adversarial attacks have shown to lead the state-of-the-art deep neural networks (DNNs) to misclassification. However, most adversarial attacks are generated according to whether they are perceptual to human visual system, measured by geometric metrics such as the l2-norm, which ignores the common watermarks in cyber-physical systems. In this paper, we propose a fast adversarial watermark attack (FAWA) method based on fast differential evolution technique, which optimally superimposes a watermark on an image to fool DNNs. We also attempt to explain the reason why the attack is successful and propose two hypotheses on the vulnerability of DNN classifiers and the influence of the watermark attack on higher-layer features extraction respectively. In addition, we propose two countermeasure methods against FAWA based on random rotation and median filtering respectively. Experimental results show that our method achieves 41.3% success rate in fooling VGG-16 and have good transferability. Our approach is also shown to be effective in deceiving deep learning as a service (DLaaS) systems as well as the physical world. The proposed FAWA, hypotheses, and the countermeasure methods, provide a timely help for DNN designers to gain some knowledge of model vulnerability while designing DNN classifiers and related DLaaS applications.

Understanding complex interactions in biomedical networks is crucial for advancements in biomedicine, but traditional link prediction (LP) methods are limited in capturing this complexity. Representation-based learning techniques improve prediction accuracy by mapping nodes to low-dimensional embeddings, yet they often struggle with interpretability and scalability. We present BioPathNet, a novel graph neural network framework based on the Neural Bellman-Ford Network (NBFNet), addressing these limitations through path-based reasoning for LP in biomedical knowledge graphs. Unlike node-embedding frameworks, BioPathNet learns representations between node pairs by considering all relations along paths, enhancing prediction accuracy and interpretability. This allows visualization of influential paths and facilitates biological validation. BioPathNet leverages a background regulatory graph (BRG) for enhanced message passing and uses stringent negative sampling to improve precision. In evaluations across various LP tasks, such as gene function annotation, drug-disease indication, synthetic lethality, and lncRNA-mRNA interaction prediction, BioPathNet consistently outperformed shallow node embedding methods, relational graph neural networks and task-specific state-of-the-art methods, demonstrating robust performance and versatility. Our study predicts novel drug indications for diseases like acute lymphoblastic leukemia (ALL) and Alzheimer’s, validated by medical experts and clinical trials. We also identified new synthetic lethality gene pairs and regulatory interactions involving lncRNAs and target genes, confirmed through literature reviews. BioPathNet’s interpretability will enable researchers to trace prediction paths and gain molecular insights, making it a valuable tool for drug discovery, personalized medicine and biology in general.

The link prediction problem is a time-evolving model in network science that has simultaneously abetted myriad applications and experienced extensive methodological improvement. Inferring the possibility of emerging links in dynamic social networks, also known as the dynamic link prediction task, is complex and challenging. In contrast to the link prediction in cross-sectional networks, dynamic link prediction methods need to cater to the actor-level temporal changes and associated evolutionary information regarding their micro- (i.e., link formation/deletion) and mesoscale (i.e., community formation) network structure. With the advent of abundant community detection algorithms, the research community has examined community-aware link prediction strategies in static networks. However, the same task in dynamic networks where, apart from the actors and links among them, their community pattern is also dynamic, is yet to be explored. Evolutionary community-aware information, including the associated link structure and temporal neighborhood changes, can effectively be mined to build dynamic similarity metrics for dynamic link prediction. This study aims to develop and integrate such dynamic features with machine learning algorithms for link prediction tasks in dynamic social networks. It also compares the performances of these features against well-known similarity metrics (i.e., ResourceAllocation) for static networks and a time series-based link prediction strategy in dynamic networks. These proposed features achieved high-performance scores, representing them as prospective candidates for both dynamic link prediction tasks and modeling the network growth.

Many link prediction methods have been developed to infer unobserved links or predict missing links based on the observed network structure that is always incomplete and subject to interfering noise. Thus, the performance of existing methods is usually limited in that their computation depends only on input graph structures, and they do not consider external information. The effects of social influence and homophily suggest that both network structure and node attribute information should help to resolve the task of link prediction. This work proposes SASNMF, a link prediction unified framework based on non-negative matrix factorization that considers not only graph structure but also the internal and external auxiliary information, which refers to both the node attributes and the structural latent feature information extracted from the network. Furthermore, three different combinations of internal and external information are proposed and input into the framework to solve the link prediction problem. Extensive experimental results on thirteen real networks, five node attribute networks and eight non-attribute networks show that the proposed framework has competitive performance compared with benchmark methods and state-of-the-art methods, indicating the superiority of the presented algorithm.

Introduction Network representation can give a holistic view of relationships for biomedical entities through network topology. Link prediction estimates the probability of link formation between the pair of unconnected nodes. In the drug discovery process, the link prediction method not only enables the detection of connectivity patterns but also predicts the effects of one biomedical entity to multiple entities simultaneously and vice versa, which is useful for many applications. Areas covered The authors provide a comprehensive overview of network link prediction in drug discovery. Link prediction methodologies such as similarity-based approaches, embedding-based approaches, probabilistic model-based approaches, and preprocessing methods are summarized with examples. In addition to describing their properties and limitations, the authors discuss the applications of link prediction in drug discovery based on the relationship between biomedical concepts. Expert opinion Link prediction is a powerful method to infer the existence of novel relationships in drug discovery. However, link prediction has been hampered by the sparsity of data and the lack of negative links in biomedical networks. With preprocessing to balance positive and negative samples and the collection of more data, the authors believe it is possible to develop more reliable link prediction methods that can become invaluable tools for successful drug discovery.

Link prediction is widely used in network analysis to identify future links between nodes. Link prediction has an important place in terms of being applicable to many real-world networks with dynamic structure. Networks with dynamic structure, such as social networks, scientific collaboration networks and metabolic networks, are networks in which link prediction studies are performed. In addition, it is seen that there are few studies showing the feasibility of link prediction by creating networks from different areas. In this study, in order to show the applicability of link prediction processes in different fields link prediction was made by applying traditional link prediction methods in the networks formed from the data of football competitions played after the groups between the years 2004–2017 in the UEFA European League. The AUC metric was used to measure the success of forecasting. The results show that link prediction methods can be used in sports networks.

Deep models can be made scale-invariant when trained with multi-scale information. Images can be easily made multi-scale, given their grid-like structures. Extending this to generic graphs poses major challenges. For example, in link prediction tasks, inputs are represented as graphs consisting of nodes and edges. Currently, the state-of-the-art model for link prediction uses supervised heuristic learning, which learns graph structure features centered on two target nodes. It then learns graph neural networks to predict the existence of links based on graph structure features. Thus, the performance of link prediction models highly depends on graph structure features. In this work, we propose a novel node aggregation method that can transform the enclosing subgraph into different scales and preserve the relationship between two target nodes for link prediction. A theory for analyzing the information loss during the re-scaling procedure is also provided. Graphs in different scales can provide scale-invariant information, which enables graph neural networks to learn invariant features and improve link prediction performance. Our experimental results on 14 datasets from different areas demonstrate that our proposed method outperforms the state-of-the-art methods by employing multi-scale graphs without additional parameters.

During the last decade, the cybersecurity literature has conferred a high-level role to machine learning as a powerful security paradigm to recognise malicious software in modern anti-malware systems. However, a non-negligible limitation of machine learning methods used to train decision models is that adversarial attacks can easily fool them. Adversarial attacks are attack samples produced by carefully manipulating the samples at the test time to violate the model integrity by causing detection mistakes. In this paper, we analyse the performance of five realistic target-based adversarial attacks, namely Extend, Full DOS, Shift, FGSM padding + slack and GAMMA, against two machine learning models, namely MalConv and LGBM, learned to recognise Windows Portable Executable (PE) malware files. Specifically, MalConv is a Convolutional Neural Network (CNN) model learned from the raw bytes of Windows PE files. LGBM is a Gradient-Boosted Decision Tree model that is learned from features extracted through the static analysis of Windows PE files. Notably, the attack methods and machine learning models considered in this study are state-of-the-art methods broadly used in the machine learning literature for Windows PE malware detection tasks. In addition, we explore the effect of accounting for adversarial attacks on securing machine learning models through the adversarial training strategy. Therefore, the main contributions of this article are as follows: (1) We extend existing machine learning studies that commonly consider small datasets to explore the evasion ability of state-of-the-art Windows PE attack methods by increasing the size of the evaluation dataset. (2) To the best of our knowledge, we are the first to carry out an exploratory study to explain how the considered adversarial attack methods change Windows PE malware to fool an effective decision model. (3) We explore the performance of the adversarial training strategy as a means to secure effective decision models against adversarial Windows PE malware files generated with the considered attack methods. Hence, the study explains how GAMMA can actually be considered the most effective evasion method for the performed comparative analysis. On the other hand, the study shows that the adversarial training strategy can actually help in recognising adversarial PE malware generated with GAMMA by also explaining how it changes model decisions.

Improving embedding-based link prediction performance using clustering