SQL injection attack is considered one of the most dangerous vulnerabilities exploited to leak sensitive information, gain unauthorized access, and cause financial loss to individuals and organizations. Conventional defense approaches use static and heuristic methods to detect previously known SQL injection attacks. Existing research uses machine learning techniques that have the capability of detecting previously unknown and novel attack types. Taking advantage of deep learning to improve detection accuracy, we propose using a probabilistic neural network (PNN) to detect SQL injection attacks. To achieve the best value in selecting a smoothing parament, we employed the BAT algorithm, a metaheuristic algorithm for optimization. In this study, a dataset consisting of 6000 SQL injections and 3500 normal queries was used. Features were extracted based on tokenizing and a regular expression and were selected using Chi-Square testing. The features used in this study were collected from the network traffic and SQL queries. The experiment results show that our proposed PNN achieved an accuracy of 99.19% with a precision of 0.995%, a recall of 0.981%, and an F-Measure of 0.928% when employing a 10-fold cross-validation compared to other classifiers in different scenarios.

The web application has become a primary target for cyber criminals by injecting malware especially JavaScript to perform malicious activities for impersonation. Thus, it becomes an imperative to detect such malicious code in real time before any malicious activity is performed. This study proposes an efficient method of detecting previously unknown malicious java scripts using an interceptor at the client side by classifying the key features of the malicious code. Feature subset was obtained by using wrapper method for dimensionality reduction. Supervised machine learning classifiers were used on the dataset for achieving high accuracy. Experimental results show that our method can efficiently classify malicious code from benign code with promising results.

Cell-Free mMIMO is a part of technology that will be integrated with future 6G ultra-dense cellular networks to ensure unlimited wireless connectivity and ubiquitous latency-sensitive services. Cell-Free gained researchers’ interest as it offers ubiquitous communication with large bandwidth, high throughput, high data transmission, and greater signal gain. Cell-Free eliminates the idea of cell boundary in cellular communication that reduces frequent handover and inter-cell interference issues. However, the effectiveness of the current authentication protocol could become a serious issue due to the dynamic nature of Cell-Free in densely distributed, high number of users, high mobility, and frequent data exchange. Secondly, secure communication may be achieved in such a dynamic environment at the expense of high authentication overhead, high communication and computational costs. To address the above security challenges, we proposed a lightweight multifactor mutual authentication protocol for Cell-Free communication using ECC-based Deffie Hellman (ECDH). This scheme utilizes timestamping, one-way hash function, Blind-Fold Challenge scheme with public key infrastructure. The proposed cryptosystem integrates with blockchain technology using proof of staked (POS) as a consensus mechanism to ensure integrity, non-repudiation and traceability. The proposed scheme can enforce the mitigation of several major security attacks on communication links such as spoofing attacks, eavesdropping, user location privacy issues, replay attacks, denial of service attacks, and man-in-the-middle (MITM) attacks, which is one of the significant features of the scheme. Furthermore, this scheme contributes to reducing authentication, communication, and computational overheads with an average of 32.8%, 52.4% and 53.2% better performance respectively as compared baseline authentication protocols.

With increased interest in 6G (6th Generation) cellular networks that can support intelligently small-cell communication will result in effective device-to-device (D2D) communication. High throughput requirement in 5G/6G cellular technology requires each device to act as intelligent transmission relays. Inclusion of such intelligence relays and support of quantum computing at D2D may compromise existing security mechanisms and may lead towards primitive attacks such as impersonation attack, rouge device attack, replay attack, MITM attack, and DoS attack. Thus, an effective yet lightweight security scheme is required that can support existing low computation devices and can address the challenges that 5G/6G poses. This paper proposes a Lightweight ECC (elliptic curve cryptography)-based Multifactor Authentication Protocol (LEMAP) for miniaturized mobile devices. LEMAP is the extension of our previous published work TLwS (trust-based lightweight security scheme) which utilizes ECC with Elgamal for achieving lightweight security protocol, confidentiality, integrity, and non-repudiation. Multi-factor Authentication is based on OTP (Biometrics, random number), timestamp, challenge, and password. This scheme has mitigated the above-mentioned attacks with significantly lower computation cost, communication cost, and authentication overhead. We have proven the correctness of the scheme using widely accepted Burrows-Abadi-Needham (BAN) logic and analyzed the performance of the scheme by using a simulator. The security analysis of the scheme has been conducted using the Discrete Logarithm Problem to verify any quantum attack possibility. The proposed scheme works well for 5G/6G cellular networks for single and multihop scenarios.

The rapid growth and uptake of network-based communication technologies have made cybersecurity a significant challenge as the number of cyber-attacks is also increasing. A number of detection systems are used in an attempt to detect known attacks using signatures in network traffic. In recent years, researchers have used different machine learning methods to detect network attacks without relying on those signatures. The methods generally have a high false-positive rate which is not adequate for an industry-ready intrusion detection product. In this study, we propose and implement a new method that relies on a modular deep neural network for reducing the false positive rate in the XSS attack detection system. Experiments were performed using a dataset consists of 1000 malicious and 10000 benign sample. The model uses 50 features selected by using Pearson correlation method and will be used in the detection and preventions of XSS attacks. The results obtained from the experiments depict improvement in the detection accuracy as high as 99.96% compared to other approaches.

Nowadays, the organizations are emphasizing on the security and resilient aspect of the cloud computing to protect the privacy and confidentiality of their data information. However, the hypervisor attack remains a hot issue by the cloud user even though enormous research have accomplished to inhibit the vulnerabilities in the virtualized cloud environment. Therefore, we have proposed the Virtual Machines and Hypervisor Intrusion Detection System, VMHIDS as our technique in detecting and preventing the hypervisor attacks in the virtualized cloud environment. The VMHIDS has adopted several features from the other techniques by inspecting the tasks frequently which then prevent suspicious event occur. Through the VMHIDS, the hypervisor attack is mitigated.