Neural Computing and Applications

Basati, Amir; Faghih, Mohammad Mehdi

doi: 10.1007/s00521-021-06011-9pmid: N/A

In recent years, the world has dramatically moved toward using the internet of things (IoT), and the IoT has become a hot research field. Among various aspects of IoT, real-time cyber-threat protection is one of the most crucial elements due to the increasing number of cyber-attacks. However, current IoT devices often offer minimal security features and are vulnerable to cyber-attacks. Therefore, it is crucial to develop tools to detect such attacks in real time. This paper presents a new and intelligent network intrusion detection system named APAE that is based on an asymmetric parallel auto-encoder and is able to detect various attacks in IoT networks. The encoder part of APAE has a lightweight architecture that contains two encoders in parallel, each one having three successive layers of convolutional filters. The first encoder is for extracting local features using standard convolutional layers and a positional attention module. The second encoder also extracts the long-range information using dilated convolutional layers and a channel attention module. The decoder part of APAE is different from its encoder and has eight successive transposed convolution layers. The proposed APAE approach has a lightweight and suitable architecture for real-time attack detection and provides very good generalization performance even after training using very limited training records. The efficacy of the APAE has been evaluated using three popular public datasets named UNSW-NB15, CICIDS2017, and KDDCup99, and the results showed the superiority of the proposed model over the state-of-the-art algorithms.

Chawla, Astha; Agrawal, Prakhar; Panigrahi, Bijaya Ketan; Paul, Kolin

doi: 10.1007/s00521-021-06106-3pmid: N/A

Cyber-attacks on smart-grid systems have become increasingly more complicated, and there is a need for taking detection and mitigation measures to combat their adverse effects on the smart-grid infrastructure. Wide area measurement system (WAMS) infrastructure comprising of phasor measurement units (PMUs) has recently shown remarkable progress in solving complex power system problems and avoiding blackouts. However, WAMS is vulnerable to cyber-attacks. This paper presents a novel cyber-attack resilient WAMS framework incorporating both attack detection and mitigation modules that ensure the resiliency of PMU data-based supervisory protection applications. It includes deep learning-based Long Short Term Memory (LSTM) model for real-time detection of anomalies in time-series PMU measurements and isolating the compromised PMUs followed by Generative Adversarial Imputation Nets (GAIN) for the reconstruction of the compromised PMU’s data. The corrected PDC data-stream is then forwarded to the decision-making end application, making it resilient against attacks. A Random Forrest classifier is used in the end application to distinguish fault events from other disturbances and supervise the third zone of distance relay for backup protection of transmission lines. The efficacy of the proposed framework for different attack scenarios has been verified on the WSCC 9-Bus System modeled on a developed real-time digital simulator (RTDS)-based integrated cyber-physical WAMS testbed. Experimental analysis shows that the proposed model successfully detects and mitigates attacks’ adverse effects on the end application.

Yasmin, Ghazaala; Chowdhury, Sujit; Nayak, Janmenjoy; Das, Priyanka; Das, Asit Kumar

doi: 10.1007/s00521-021-06132-1pmid: N/A

Video summarization is the process of refining the original video into a more concise form without losing valuable information. Both efficient storage and extraction of valuable information from a video are the challenging tasks in video analysis. Intelligent video surveillance system has an essential role for ensuring safety and security to the public. Recent intelligent technologies are extensively using the surveillance systems in all areas starting from border security application to street monitoring systems. Now the surveillance camera or motion sensitivity-based cameras produce large volume of data when employed for recording videos. As analysis of videos by humans demands immense manpower, automatic video summarization is an important and growing research topic. Hence, it is necessary to summarize the activities in the scene and eliminate unusual and redundant events recorded in videos. The proposed work has developed a video summarization framework using key moment-based frame selection and clustering of frames to identify only informative frames. The key moment is a simple yet effective characteristic for summarizing a long video shot and motion is the most salient feature in presenting actions or events in video which is used here to extract the key moments of the video frames. The motion is the scene of a video frame which has the most acceleration and deceleration in case of the key moments. Based on the extracted key moments, the frames of the video are partitioned into different groups using a novel similarity-based agglomerative clustering algorithm. The algorithm determines at most K clusters of frames based on Jaccard similarity among the clusters, where K is the user defined parameter set as the 5% to 15% of the size of the video to be summarized. From each cluster, few representative frames are identified based on the centroids of the clusters and arranged according to their original video sequence to generate the summary of the video. The proposed clustering algorithm and the summarization method are evaluated using state-of-the-art video datasets and compared with some related methodologies to demonstrate their effectiveness.

Ajij, Md; Pratihar, Sanjoy; Nayak, Soumya Ranjan; Hanne, Thomas; Roy, Diptendu Sinha

doi: 10.1007/s00521-021-05854-6pmid: N/A

Verifying the genuineness of official documents, such as bank checks, certificates, contract forms, bonds, etc., remains a challenging task when it comes to accuracy and robustness. Here, the genuineness is related to the degree of match of the signature contained in the documents relating to the original signatures of the authorized person. Signatures of authorized persons are considered known in advance.In this paper, a novel feature set is introduced based on quasi-straightness of boundary pixel runs for signature verification. We extract the quasi-straight line segments using elementary combinations of the directional codes from the signature boundary pixels and subsequently we obtain the feature set from various quasi-straight line classes. The quasi-straight line segments provide a blending of straightness and small curvatures resulting in a robust feature set for the verification of signatures. We have used Support Vector Machine (SVM) for classification and have shown results on standard signature datasets like CEDAR (Center of Excellence for Document Analysis and Recognition) and GPDS-100 (Grupo de Procesado Digital de la Senal).The results establish how the proposed method outperforms the existing state of the art.

Ozcan, Alper; Catal, Cagatay; Donmez, Emrah; Senturk, Behcet

doi: 10.1007/s00521-021-06401-zpmid: 34393380

Phishing is an attack targeting to imitate the official websites of corporations such as banks, e-commerce, financial institutions, and governmental institutions. Phishing websites aim to access and retrieve users’ important information such as personal identification, social security number, password, e-mail, credit card, and other account information. Several anti-phishing techniques have been developed to cope with the increasing number of phishing attacks so far. Machine learning and particularly, deep learning algorithms are nowadays the most crucial techniques used to detect and prevent phishing attacks because of their strong learning abilities on massive datasets and their state-of-the-art results in many classification problems. Previously, two types of feature extraction techniques [i.e., character embedding-based and manual natural language processing (NLP) feature extraction] were used in isolation. However, researchers did not consolidate these features and therefore, the performance was not remarkable. Unlike previous works, our study presented an approach that utilizes both feature extraction techniques. We discussed how to combine these feature extraction techniques to fully utilize from the available data. This paper proposes hybrid deep learning models based on long short-term memory and deep neural network algorithms for detecting phishing uniform resource locator and evaluates the performance of the models on phishing datasets. The proposed hybrid deep learning models utilize both character embedding and NLP features, thereby simultaneously exploiting deep connections between characters and revealing NLP-based high-level connections. Experimental results showed that the proposed models achieve superior performance than the other phishing detection models in terms of accuracy metric.

Mishra, Sandhya; Soni, Devpriya

doi: 10.1007/s00521-021-06305-ypmid: 34341626

With the origin of smart homes, smart cities, and smart everything, smart phones came up as an area of magnificent growth and development. These devices became a part of daily activities of human life. This impact and growth have made these devices more vulnerable to attacks than other devices such as desktops or laptops. Text messages or SMS (Short Text Messages) are a part of smartphones through which attackers target the users. Smishing (SMS Phishing) is an attack targeting smartphone users through the medium of text messages. Though smishing is a type of phishing, it is different from phishing in many aspects like the amount of information available in the SMS, the strategy of attack, etc. Thus, detection of smishing is a challenge in the context of the minimum amount of information shared by the attacker. In the case of smishing, we have short text messages which are often in short forms or in symbolic forms. A single text message contains very few smishing-related features, and it consists of abbreviations and idioms which makes smishing detection more difficult. Detection of smishing is a challenge not only because of features constraint but also due to the scarcity of real smishing datasets. To differentiate spam messages from smishing messages, we are evaluating the legitimacy of the URL (Uniform Resource Locator) in the message. We have extracted the five most efficient features from the text messages to enable the machine learning classification using a limited number of features. In this paper, we have presented a smishing detection model comprising of two phases, Domain Checking Phase and SMS Classification Phase. We have examined the authenticity of the URL in the SMS which is a crucial part of SMS phishing detection. In our system, Domain Checking Phase scrutinizes the authenticity of the URL. SMS Classification Phase examines the text contents of the messages and extracts some efficient features. Finally, the system classifies the messages using Backpropagation Algorithm and compares results with three traditional classifiers. A prototype of the system has been developed and evaluated using SMS datasets. The results of the evaluation achieved an accuracy of 97.93% which shows the proposed method is very efficient for the detection of smishing messages.

Ding, Hongwei; Chen, Leiyang; Tao, Qi; Fu, Zhongwang; Dong, Liang; Cui, Xiaohui

doi: 10.1007/s00521-021-06329-4pmid: 34404963

The detection and location of image splicing forgery are a challenging task in the field of image forensics. It is to study whether an image contains a suspicious tampered area pasted from another image. In this paper, we propose a new image tamper location method based on dual-channel U-Net, that is, DCU-Net. The detection framework based on DCU-Net is mainly divided into three parts: encoder, feature fusion, and decoder. Firstly, high-pass filters are used to extract the residual of the tampered image and generate the residual image, which contains the edge information of the tampered area. Secondly, a dual-channel encoding network model is constructed. The input of the model is the original tampered image and the tampered residual image. Then, the deep features extracted from the dual-channel encoding network are fused for the first time, and then the tampered features with different granularity are extracted by dilation convolution, and then, the secondary fusion is carried out. Finally, the fused feature map is input into the decoder, and the predicted image is decoded layer by layer. The experimental results on Casia2.0 and Columbia datasets show that DCU-Net performs better than the latest algorithm and can accurately locate tampered areas. In addition, the attack experiments show that DCU-Net model has good robustness and can resist noise and JPEG recompression attacks.

Kenger, Ömer Nedim; Özceylan, Eren

doi: 10.1007/s00521-023-08267-9pmid: N/A

The amount of digital data in the universe is growing at an exponential rate with the rapid development of digital information, and this reveals new machine learning methods. Learning algorithms using hyperboxes are a subsection of machine learning methods. Fuzzy min–max neural network (FMNN) are one of the most common and advanced methods using hyperboxes. FMNN is a special type of NeuroFuzzy system that combines the artificial neural network and fuzzy set into a common framework. This paper conducts an extensive bibliometric and network analysis of FMNN literature. Two hundred and sixty-two publications are analysed from the period of 1992–2022. Several analyses are realized in order to identify trends, challenges and key points in a more scientific and objective way that affect the development of knowledge in the FMNN domain. It can be seen from bibliometric analysis that there is rapid development in the last 10 years. Social network analysis results show that Chee Peng Lim is the most active author in the network. Besides, the modifications of FMNN are generally developed for classification. However, there are still potential future research opportunities for clustering.

Alturayeif, Nora; Luqman, Hamzah; Ahmed, Moataz

doi: 10.1007/s00521-023-08285-7pmid: 36743664

Stance detection is an evolving opinion mining research area motivated by the vast increase in the variety and volume of user-generated content. In this regard, considerable research has been recently carried out in the area of stance detection. In this study, we review the different techniques proposed in the literature for stance detection as well as other applications such as rumor veracity detection. Particularly, we conducted a systematic literature review of empirical research on the machine learning (ML) models for stance detection that were published from January 2015 to October 2022. We analyzed 96 primary studies, which spanned eight categories of ML techniques. In this paper, we categorize the analyzed studies according to a taxonomy of six dimensions: approaches, target dependency, applications, modeling, language, and resources. We further classify and analyze the corresponding techniques from each dimension’s perspective and highlight their strengths and weaknesses. The analysis reveals that deep learning models that adopt a mechanism of self-attention have been used more frequently than the other approaches. It is worth noting that emerging ML techniques such as few-shot learning and multitask learning have been used extensively for stance detection. A major conclusion of our analysis is that despite that ML models have shown to be promising in this field, the application of these models in the real world is still limited. Our analysis lists challenges and gaps to be addressed in future research. Furthermore, the taxonomy presented can assist researchers in developing and positioning new techniques for stance detection-related applications.

Huang, Gaofeng; Jafari, Amir Hossein

doi: 10.1007/s00521-021-06163-8pmid: 34177125

Generative adversarial networks (GANs) are one of the most powerful generative models, but always require a large and balanced dataset to train. Traditional GANs are not applicable to generate minority-class images in a highly imbalanced dataset. Balancing GAN (BAGAN) is proposed to mitigate this problem, but it is unstable when images in different classes look similar, e.g., flowers and cells. In this work, we propose a supervised autoencoder with an intermediate embedding model to disperse the labeled latent vectors. With the enhanced autoencoder initialization, we also build an architecture of BAGAN with gradient penalty (BAGAN-GP). Our proposed model overcomes the unstable issue in original BAGAN and converges faster to high-quality generations. Our model achieves high performance on the imbalanced scale-down version of MNIST Fashion, CIFAR-10, and one small-scale medical image dataset. https://github.com/GH920/improved-bagan-gp.