Internet usage has grown exponentially, with individuals and companies performing multiple daily transactions in cyberspace rather than in the real world. The coronavirus (COVID-19) pandemic has accelerated this process. As a result of the widespread usage of the digital environment, traditional crimes have also shifted to the digital space. Emerging technologies such as cloud computing, the Internet of Things (IoT), social media, wireless communication, and cryptocurrencies are raising security concerns in cyberspace. Recently, cyber criminals have started to use cyber attacks as a service to automate attacks and leverage their impact. Attackers exploit vulnerabilities that exist in hardware, software, and communication layers. Various types of cyber attacks include distributed denial of service (DDoS), phishing, man-in-the-middle, password, remote, privilege escalation, and malware. Due to new-generation attacks and evasion techniques, traditional protection systems such as firewalls, intrusion detection systems, antivirus software, access control lists, etc., are no longer effective in detecting these sophisticated attacks. Therefore, there is an urgent need to find innovative and more feasible solutions to prevent cyber attacks. The paper first extensively explains the main reasons for cyber attacks. Then, it reviews the most recent attacks, attack patterns, and detection techniques. Thirdly, the article discusses contemporary technical and nontechnical solutions for recognizing attacks in advance. Using trending technologies such as machine learning, deep learning, cloud platforms, big data, and blockchain can be a promising solution for current and future cyber attacks. These technological solutions may assist in detecting malware, intrusion detection, spam identification, DNS attack classification, fraud detection, recognizing hidden channels, and distinguishing advanced persistent threats. However, some promising solutions, especially machine learning and deep learning, are not resistant to evasion techniques, which must be considered when proposing solutions against intelligent cyber attacks.

Recent technological developments in computer systems transfer human life from real to virtual environments. Covid-19 disease has accelerated this process. Cyber criminals’ interest has shifted in a real to virtual life as well. This is because it is easier to commit a crime in cyberspace rather than regular life. Malicious software (malware) is unwanted software which is frequently used by cyber criminals to launch cyber-attacks. Malware variants are continuing to evolve by using advanced obfuscation and packing techniques. These concealing techniques make malware detection and classification significantly challenging. Novel methods which are quite different from traditional methods must be used to effectively combat with new malware variants. Traditional artificial intelligence (AI) specifically machine learning (ML) algorithms are no longer effective in detecting all new and complex malware variants. Deep learning (DL) approach which is quite different from traditional ML algorithms can be a promising solution to the problem of detecting all variants of malware. In this study, a novel deep-learning-based architecture is proposed which can classify malware variants based on a hybrid model. The main contribution of the study is to propose a new hybrid architecture which integrates two wide-ranging pre-trained network models in an optimized manner. This architecture consists of four main stages, namely: data acquisition, the design of deep neural network architecture, training of the proposed deep neural network architecture, and evaluation of the trained deep neural network. The proposed method tested on Malimg, Microsoft BIG 2015, and Malevis datasets. The experimental results show that the suggested method can effectively classify malware with high accuracy which outperforms the state of the art methods in the literature. When proposed method tested on Malimg dataset, 97.78% accuracy is obtained which is outperformed most of the ML-based malware detection method.

Recognition of human actions in partially cluttered environments is an important research field of computer vision and human–computer interaction. This field has recently garnered attention from a large number of academic researchers in various fields of application. This study proposes a novel deep-learning-based architecture for the recognition and prediction of human actions based on a hybrid model. The main contribution of this study is to propose a new hybrid architecture, integrating four wide-ranging pre-trained network models in an optimized manner, using a metaheuristic algorithm. This architecture consists of four main stages: namely, the creation of the data set, the design of deep neural network (DNN) architecture, training and optimization of the proposed DNN architecture, and evaluation of the trained DNN. By adapting the aforementioned architecture, reliable features are obtained for the training procedure. In order to validate the superiority of the proposed architecture over other state-of-the-art studies, a performance evaluation between these architectures is presented using benchmark datasets. The results reveal that the proposed architecture outperforms previously developed architectures in terms of predicting human actions.

Intrusion detection systems (IDSs) are employed to maintain computer networks from cyber attacks. Here, the aim is to detect intrusions once the data is transmitted across the internet. Intrusion detection methods (IDMs) developed in the literature are commonly focused on data mining, statistical and machine learning-based analysis of anomaly situations. In this paper, we suggested machine learning based methodology to detect intrusions in computer networks. The proposed method comprises four main phases, namely, preprocessing, feature selection, parameter optimization and classification. Most significant features are selected by utilizing the Correlation Based Feature Selection. For classification Random Tree, AdaBoost, K-Nearest Neighbor (KNN), Support-vector machine (SVM) are used while for parameter optimization particle swarm optimization is employed. The proposed method was tested on two extensive datasets, namely NSL-KDD and CIC-DDOS2019. The experimental results reveal that the proposed method can effectively classify intrusions with a high detection rate and that it outperforms the other machine learning techniques.

Intrusion detection plays a significant role in the provision of information security. The most critical element is the ability to precisely identify different types of intrusions into the network. However, the detection of intrusions poses a important challenge, as many new types of intrusion are now generated by cyber-attackers every day. A robust system is still elusive, despite the various strategies that have been proposed in recent years. Hence, a novel deep-learning-based architecture for detecting intrusions into a computer network is proposed in this paper. The aim is to construct a hybrid system that enhances the efficiency and accuracy of intrusion detection. The main contribution of our work is a novel deep learning-based hybrid architecture in which PSO is used for hyperparameter optimisation and three well-known pre-trained network models are combined in an optimised way. The suggested method involves six key stages: data gathering, pre-processing, deep neural network (DNN) architecture design, optimisation of hyperparameters, training, and evaluation of the trained DNN. To verify the superiority of the suggested method over alternative state-of-the-art schemes, it was evaluated on the KDDCUP’99, NSL-KDD and UNSW-NB15 datasets. Our empirical findings show that the proposed model successfully and correctly classifies different types of attacks with 82.44%, 90.42% and 93.55% accuracy values obtained on UNSW-B15, NSL-KDD and KDDCUP’99 datasets, respectively, and outperforms alternative schemes in the literature.

The detection of fraudulent activities in credit cards transactions presents a significant challenge due to the constantly changing and unpredictable tactics used by fraudsters, who take advantage of technological advancements to evade security measures and cause substantial financial harm. In this paper, we suggested a machine learning based methodology to detect fraud in credit cards. The suggested method contains four key phases, including data normalization, data preprocessing, feature selection, classification. For classification artificial neural network, decision tree, logistic regression, naive bayes, random forest while for feature selection particle swarm optimization is employed. With the use of a dataset created from European cardholders, the suggested method was tested. The experimental results show that the suggested method beats the other machine learning techniques and can successfully classify frauds with a high detection rate.