Suliman A. Alsuhibany

A Completely Automated Public Turing test to tell Computers and Humans Apart (CAPTCHA) is a widely adopted security mechanism used to distinguish human users from automated programs and mitigate cyberattacks. Given the extensive use of the Internet among Arabic speakers, Arabic CAPTCHA systems have attracted increasing research attention in recent years. Prior studies indicate that handwritten text-based CAPTCHAs provide enhanced security compared to their printed counter-parts. This study proposes the development of a handwritten Arabic CAPTCHA generator based on Saudi fonts, aiming to preserve linguistic and cultural identity while achieving a balanced trade-off between security and usability. The proposed framework introduces a structured classification model for Saudi calligraphic fonts and evaluates their effectiveness using both meaningful and meaningless Arabic words. To further enhance robustness against automated attacks, the adversarial perturbation technique Jacobian-based Saliency Map Attack (JSMA) is applied to the generated CAPTCHA samples. Extensive experimental evaluations are conducted to assess security resistance using optical character recognition (OCR)-based attacks, alongside usability testing involving human participants. The results demonstrate that Saudi handwritten calligraphic fonts can significantly improve CAPTCHA robustness while maintaining acceptable usability levels. From a security perspective, it achieves an Optical Character Recognition (OCR) recognition rate of 90%, the human accuracy reaches 88%, and the average solving time is 9.6 s. These findings highlight the potential of culturally grounded handwritten Arabic CAPTCHA systems as effective authentication mechanisms in modern cybersecurity applications.

The extensive integration of QR codes into daily activities highlights their pivotal role in facilitating seamless information exchange. However, this widespread adoption also exposes QR codes to cybersecurity threats. Malicious QR codes, often persuasive as legitimate code, can carry unwanted or harmful content, posing significant risks to users. Particularly, the encoded information within QR codes, including URLs, is a prime target for cybercriminals. Consequently, to effectively mitigate these threats, precise detection systems are imperative for identifying novel instances of malicious URLs embedded within QR codes. Traditional approaches, like blacklists, are increasingly inadequate against the evolving threat landscape. Therefore, there has been a shift towards leveraging pre-trained language modelling techniques as a more robust solution to enhance QR code security. This study aims to harness the power of a BERT-based architecture to differentiate and classify QR codes based on the URLs embedded within them, distinguishing between benign and malicious URLs. Moreover, the study adopts an adaptive and dynamic approach through periodic model refinement. By continuously updating and retraining the model with newly recorded URL data sourced from diverse resources, this methodology ensures its adaptability to evolving threats, thus fortifying QR code security measures. The experimental findings from the proposed BERT model showcase superior performance in accurately detecting malicious URLs, outperforming other methods.

Completely Automated Public Turing tests to Tell Computers and Humans Apart (CAPTCHAs) are among the most widely used applications of Artificial Intelligence (AI) for enhancing web security. Recently, Arabic CAPTCHAs have begun to attract research attention, though studies focusing on handwritten Arabic CAPTCHAs remain limited. This paper explores the usability of a proposed handwritten Arabic CAPTCHA model designed not only to differentiate between humans and bots but also to serve as a tool for supporting Arabic language learning. The model incorporates handwritten Arabic letters and words in a gamified format to aid in character recognition and engagement. To address the lack of usability evaluations in this area, the study empirically assesses the model's effectiveness and efficiency. Results indicate that meaningful handwritten text led to strong usability outcomes, with an average completion time of 4.7 seconds and an accuracy rate of 98.6%. Based on these findings, an abstract model of a language-learning-oriented CAPTCHA system is proposed. Additionally, the study identifies several usability challenges that should be addressed in future development to improve user experience and educational value

Barcode technology is widely used as an automated identification system that enables rapid and efficient data capture, particularly in retail environments. Despite its practicality, barcode-based systems are increasingly vulnerable to security threats—most notably, barcode substitution fraud. To address these challenges, this paper presents an innovative system for the secure generation and verification of Quick Response (QR) codes using a digital watermarking technique. The proposed method embeds tamper-resistant information within QR codes, enhancing their integrity and making unauthorized modification more difficult. Additionally, a neural network-based authentication model was developed to verify the legitimacy of scanned QR codes. The system was evaluated through experimental testing on a dataset of 5000 QR samples. The results demonstrated high accuracy in distinguishing between genuine and fraudulent QR codes, confirming the system’s effectiveness in supporting fraud prevention in real-world applications.

With the increasing online activity of Arabic speakers, the development of effective CAPTCHAs (Completely Automated Public Turing Tests to Tell Computers and Humans Apart) tailored for Arabic users has become crucial. Traditional CAPTCHAs, however, are increasingly vulnerable to machine learning-based attacks. To address this challenge, we introduce a method for generating adversarial handwritten Arabic CAPTCHAs that remain user-friendly yet difficult for machines to solve. Our approach involves synthesizing handwritten Arabic words using a simulation technique, followed by the application of five adversarial perturbation techniques: Expectation Over Transformation (EOT), Scaled Gaussian Translation with Channel Shifts (SGTCS), Jacobian-based Saliency Map Attack (JSMA), Immutable Adversarial Noise (IAN), and Connectionist Temporal Classification (CTC). Evaluation results demonstrate that JSMA provides the highest level of security, with 30% of meaningless word CAPTCHAs remaining completely unrecognized by automated systems falling to 6.66% for meaningful words. From a usability perspective, JSMA also achieves the highest accuracy rates, with 75.6% for meaningless words and 90.6% for meaningful words. Our work presents an effective strategy for enhancing the security of Arabic websites and online interfaces against bot attacks, contributing to the advancement of CAPTCHA systems.

This article proposes a novel algorithm to address the security issues in millimeter‐wave Internet‐of‐vehicles (mmWave‐IoV). The main idea is to provide a new solution to eliminate eavesdropping in dynamic mmWave‐IoV infrastructure. For this purpose, a secure multiagent cooperative communication algorithm based on deep deterministic policy gradient (DDPG) and dueling double deep Q network (D3QN) is proposed. The eavesdropper reception signal quality is reduced by using the cooperative jamming of the road side unit (RSU). The total secrecy rate of all authentic vehicles is used as the optimization problem with the objective to maximize it using the jamming RSUs, joint beam connections of vehicular users and base station, and the transmit power and jamming direction of cooperative RSUs. A real‐time, continuous, and discrete fusion‐based decision‐making strategy is deployed by creating an RSU agent utilizing the capabilities of the DDPG‐D3QN algorithm and a vehicular user agent used in D3QN. Simulation results show that the proposed algorithm has superior performance as compared with existing algorithms.

Cyber-criminals target smart connected devices for spyware distribution and security breaches, but existing Internet of Things (IoT) security standards are insufficient. Major IoT industry players prioritize market share over security, leading to insecure smart products. Traditional host-based protection solutions are less effective due to limited resources. Overcoming these challenges and enhancing the security of IoT Devices requires a security design at the network level that uses lightweight cryptographic parameters. In order to handle control, administration, and security concerns in traditional networking, the Gateway Node offers a contemporary networking architecture. By managing all network-level computations and complexity, the Gateway Node relieves IoT devices of these responsibilities. In this study, we introduce a novel privacy-preserving security architecture for gateway-node smart homes. Subsequently, we develop Smart Homes, An Efficient, Anonymous, and Robust Authentication Scheme (EARAS) based on the foundational principles of this security architecture. Furthermore, we formally examine the security characteristics of our suggested protocol that makes use of methodology such as ProVerif, supplemented by an informal analysis of security. Lastly, we conduct performance evaluations and comparative analyses to assess the efficacy of our scheme. Performance analysis shows that EARAS achieves up to 30% to 54% more efficient than most protocols and lower computation cost compared to Banerjee et al.’s scheme, and significantly reduces communication overhead compared to other recent protocols, while ensuring comprehensive security. Our objective is to provide robust security measures for smart homes while addressing resource constraints and preserving user privacy.

Data compression plays a vital role in data management and information theory by reducing redundancy. However, it lacks built-in security features such as secret keys or password-based access control, leaving sensitive data v... | Find, read and cite all the research you need on Tech Science Press

Bloom filters are a type of data structure that is used to test whether or not an element is a member of a set. They are known for being space-efficient and are commonly employed in various applications, such as network routers, web browsers, and databases. These filters work by allowing a fixed probability of incorrectly identifying an element as being a member of the set, known as the false positive rate (FPR). However, traditional bloom filters suffer from a high FPR and extensive memory usage, which can lead to incorrect query results and a slow performance. Thus, this study indicates that a content-based strategy could be a practical solution for these challenges. Specifically, our approach requires less bloom filter storage, consequently decreasing the probability of false positives. The effectiveness of several hash functions on our strategy’s performance was also evaluated. Experimental evaluations demonstrated that the proposed strategy could potentially decrease false positives by a substantial margin of up to 79.83%. The use of size-based content bits significantly contributes to the decrease in the number of false positives as well. However, as the volume of content bits rises, the impact on time is not considerably noticeable. Moreover, the evidence suggests that the application of a singular approach leads to a more than 50% decrease in false positives.