Neural networks play an important role in satellite image classification. We know that the most common neural networks used in image classification tasks are convolutional neural networks (CNNs). In this paper, we explored the influence of the spectral bands in image classification using the Vision Transformer (ViT). Convolution is a local operation, and a convolution layer typically models only the relationships between neighborhood pixels. The transformer is a global operation, and a transformer layer can model the relationships between all pixels. This motivated us to use ViT for satellite image classification. Sentinel-2 EuroSAT image dataset, which consists of 27,000 images in ten classes, is used for the experiment. ViT model is trained with the three-band dataset, Red-Green-Blue (RGB), and compared with ViT model trained with RGB along with Near InfraRed (NIR) and with a multispectral satellite image dataset (13 bands). Experimental results show that the NIR band combined with RGB was able to produce more accurate results than RGB alone, whereas the 13 bands datasets outperformed both RGB and RGB & NIR datasets.

Malware distribution to the victim network is commonly performed through file attachments in phishing email or downloading illegitimate files from the internet, when the victim interacts with the source of infection. To detect and prevent the malware distribution in the victim machine, the existing end device security applications may leverage sophisticated techniques such as signature-based or anomaly-based, machine learning techniques. The well-known file formats Portable Executable (PE) for Windows and Executable and Linkable Format (ELF) for Linux based operating system are used for malware analysis and the malware detection capabilities of these files has been well advanced for real time detection. But the malware payload hiding in multimedia like cover images using steganography detection has been a challenge for enterprises, as these are rarely seen and usually act as a stager in sophisticated attacks. In this article, to our knowledge, we are the first to try to address the knowledge gap between the current progress in image steganography and steganalysis academic research focusing on data hiding and the review of the stegomalware (malware payload hiding in images) targeting enterprises with cyberattacks current status. We present the stegomalware history, generation tools, file format specification description. Based on our findings, we perform the detail review of the image steganography techniques including the recent Generative Adversarial Networks (GAN) based models and the image steganalysis methods including the Deep Learning opportunities and challenges in stegomalware generation and detection are presented based on our findings.

Deep Learning (DL), a novel form of machine learning (ML) is gaining much research interest due to its successful application in many classical artificial intelligence (AI) tasks as compared to classical ML algorithms (CMLAs). Recently, DL architectures are being innovatively modelled for diverse applications in the area of cyber security. The literature is now growing with DL architectures and their variations for exploring different innovative DL models and prototypes that can be tailored to suit specific cyber security applications. However, there is a gap in literature for a comprehensive survey reporting on such research studies. Many of the survey-based research have a focus on specific DL architectures and certain types of malicious attacks within a limited cyber security problem scenario of the past and lack futuristic review. This paper aims at providing a well-rounded and thorough survey of the past, present, and future DL architectures including next-generation cyber security scenarios related to intelligent automation, Internet of Things (IoT), Big Data (BD), Blockchain, cloud and edge technologies. This paper presents a tutorial-style comprehensive review of the state-of-the-art DL architectures for diverse applications in cyber security by comparing and analysing the contributions and challenges from various recent research papers. Firstly, the uniqueness of the survey is in reporting the use of DL architectures for an extensive set of cybercrime detection approaches such as intrusion detection, malware and botnet detection, spam and phishing detection, network traffic analysis, binary analysis, insider threat detection, CAPTCHA analysis, and steganography. Secondly, the survey covers key DL architectures in cyber security application domains such as cryptography, cloud security, biometric security, IoT and edge computing. Thirdly, the need for DL based research is discussed for the next generation cyber security applications in cyber physical systems (CPS) that leverage on BD analytics, natural language processing (NLP), signal and image processing and blockchain technology for smart cities and Industry 4.0 of the future. Finally, a critical discussion on open challenges and new proposed DL architecture contributes towards future research directions.

This paper proposes an architecture taking advantage of artificial intelligence and text mining techniques in order to: (i) detect paranoid people by classifying their set of tweets into two classes (Paranoid/not-Paranoid), (ii) ensure the surveillance of these people by classifying their tweets about Covid-19 into two classes (person with normal behavior, person with inappropriate behavior). These objectives are achieved using an approach that takes advantage of different information related to the textual part, user and tweets for features selection task and deep neural network for the classification task. We obtained as an F-score rate 70% for the detection of paranoid people and 73% for the detection of the behavior of these people towards Covid-19. The obtained results are motivating and encouraging researchers to improve them given the interest and the importance of this research axis.

Peer-to-Peer (P2P) Networking have a lot of practical applicability’s over the years. File storage and resource sharing are few key areas among the others where such peered network architecture is widely successful. The common building block for P2P networking is to store or locate an identifiable resource, for which there are basically 3 approaches namely (1) local storage/broadcast search (2) global storage/local search (3) distributed storage/distributed search. With the development of mobile hardware and wireless technology, it further became feasible to use mobile devices in these P2P networks. This computing architecture is widely used in Mobile Ad-hoc Network (MANET) for building content sharing applications. Search algorithm and file transfer schemes are the basic components of such content sharing systems. In this article, we provide a brief overview of the resource discovery approaches for peer-to-peer file sharing applications over MANET. We analyze and classify the search techniques into 4 broad schemes, mainly the flooding-based schemes, Distributed Hash Table (DHT) based schemes, advertisement-based schemes, and social network-based schemes. The pros and cons of each technique is summarized. Further, a one-to-one comparison is done across the classes for quick interpretation. We also outline the various issues, and complications that should be taken into consideration while designing any resource discovery algorithm. Further, we briefly discuss the security threats, and present state-of-the-art countermeasures for it. Also, we highlight some important guidelines that need to be focused while designing efficient file sharing applications and services in Mobile Edge Computing (MEC) enabled networks. Comprehensive and in-depth assessments of the related approaches are presented providing clear insights for the future research directions.

Resource discovery is an important fundamental aspect and a crucial task in Mobile Peer-to-Peer Networks (MP2P). To compliment network dynamics and churn, the unstructured search architecture is widely used. The key goal of an efficient search scheme is to find the required resource with minimal search latency, low overhead, and low power consumption to better suit the nature of mobile nodes where resource constraints are the major bottleneck. Resource discovery thus becomes an integral part of the distributed architecture and resource sharing systems. In the past, many resource discovery strategies are proposed for Mobile P2P networks. A schematic and tabular classification of these systems enables one to review the existing works under one umbrella. This article presents an overview of such several different schemes for performing resource discovery in the MP2P network broadly classified under six different categories, i.e., centralized, unstructured, structured, super node based, hybrid, and other general lookup schemes. We also give a brief comparison of P2P, MANET, and P2P MANETs. Further, we discuss various routing schemes in such an evolving network. In this survey, we study and review the existing resource discovery techniques in MP2P systems. The classification of each scheme with their advantages and disadvantages are discussed. We highlight a few open research issues, and brief the role of network topology and its structure on the performance of the resource search protocols. Further, we also glimpse on the security threats in MP2P networks and suggest their countermeasures. And, finally, a summary of each method is given, along with their lookup complexities.

In this paper, we explore the use of an attention based mechanism known as Residual Attention for malware detection and compare this with existing CNN based methods and conventional Machine Learning algorithms with the help of GIST features. The proposed method outperformed traditional malware detection methods which use Machine Learning and CNN based Deep Learning algorithms, by demonstrating an accuracy of 99.25%.

Network Intrusion Detection System (NIDS) is a method that is utilized to categorize network traffic as malicious or normal. Anomaly-based method and signature-based method are the traditional approaches used for network intrusion detection. The signature-based approach can only detect familiar attacks whereas the anomaly-based approach shows promising results in detecting new unknown attacks. Machine Learning (ML) based approaches have been studied in the past for anomaly-based NIDS. In recent years, the Deep Learning (DL) algorithms have been widely utilized for intrusion detection due to its capability to obtain optimal feature representation automatically. Even though DL based approaches improves the accuracy of the detection tremendously, they are prone to adversarial attacks. The attackers can trick the model to wrongly classify the adversarial samples into a particular target class. In this paper, the performance analysis of several ML and DL models are carried out for intrusion detection in both adversarial and non-adversarial environment. The models are trained on the NSLKDD dataset which contains a total of 148,517 data points. The robustness of several models against adversarial samples is studied.

In the present era, cyberspace is growing tremendously and the intrusion detection system (IDS) plays a key role in it to ensure information security. The IDS, which works in network and host level, should be capable of identifying various malicious attacks. The job of network-based IDS is to differentiate between normal and malicious traffic data and raise an alert in case of an attack. Apart from the traditional signature and anomaly-based approaches, many researchers have employed various deep learning (DL) techniques for detecting intrusion as DL models are capable of extracting salient features automatically from the input data. The application of deep convolutional neural network (DCNN), which is utilized quite often for solving research problems in image processing and vision fields, is not explored much for IDS. In this paper, a DCNN architecture for IDS which is trained on KDDCUP 99 data set is proposed. This work also shows that the DCNN-IDS model performs superior when compared with other existing works.

Social media is a platform in which tons and tons of text are generated each and every day. The data is so large that cannot be easily understood, so this has paved a path to a new field in the information technology which is natural language processing. In this paper, the text data which is used for the classification is tweets that determines the state of the person according of the sentiments which is positive, negative and neutral. Emotions are the way of expression of the person’s feelings which has a high influence on the decision making tasks. Here we have proposed the text representation, Term Frequency Inverse Document Frequency (tfidf), Keras embedding along with the machine learning and deep learning algorithms for the purpose of the classification of the sentiments, out of which Logistics Regression machine learning based methods out performs well when the features is taken in the limited amount as the features increases Support Vector Machine (SVM) which is also one of the machine learning algorithm out performs well making a benchmark accuracy for this dataset as the 75.8%. For the research purpose the dataset has been made publically available.

With the tremendous growth of the internet, cyberspace is facing several threats from the attackers. Threats like spam emails account for 55\% of total emails according to the Symantec monthly threat report. Over time, the attackers moved on to image spam to evade the text-based spam filters. To deal with this, the researchers have several machine learning and deep learning approaches that use various features like metadata, color, shape, texture features. But the Deep Convolutional Neural Network (DCNN) and transfer learning-based pre-trained CNN models are not explored much for Image spam classification. Therefore, in this work, 2 DCNN models along with few pre-trained ImageNet architectures like VGG19, Xception are trained on 3 different datasets. The effect of employing a Cost-sensitive learning approach to handle data imbalance is also studied. Some of the proposed models in this work achieves an accuracy up to 99\% with zero false positive rate in best case.

A document by vinayakumar R . Click on the document to view its contents.