The growing reliance on digital financial services necessitates a secure, efficient, and privacy-centric approach to identity verification and Know Your Customer (KYC) compliance. Traditional identity management systems rely on centralized databases, making them susceptible to data breaches, inefficiencies, and regulatory constraints. Over 10 billion identity records have been exposed in centralized KYC breaches, leading to a 60% increase in financial fraud cases. The rise of Decentralized Finance (DeFi) has further complicated KYC compliance, requiring innovative solutions that balance privacy and regulatory requirements. This paper proposes a Web3-powered decentralized identity framework that leverages blockchain technology, self-sovereign identity (SSI), verifiable credentials (VCs), and zero-knowledge proofs (ZKPs). By eliminating reliance on centralized authorities, our system enhances data privacy, reducing personally identifiable information (PII) disclosure by 80% while ensuring compliance with AML and GDPR regulations. The integration of zk-SNARKs enables trustless identity verification with an average proof generation time of 12.5 seconds, significantly reducing the 3–5 day verification period required by traditional systems. Smart contract-based KYC automation eliminates intermediaries, cutting compliance costs by 40% and reducing fraud risk by 60%. Through comparative analysis, we highlight that decentralized KYC improves security, cost-effectiveness, and scalability compared to traditional models. Performance evaluation confirms that transaction throughput remains within acceptable blockchain limits, with gas costs stabilized at 35,000–55,000 Gwei per verification request. Despite challenges in regulatory adaptation and zk-SNARK scalability, the proposed model demonstrates the feasibility of Web3-driven identity management for trustless, privacy-preserving, and compliant financial ecosystems.

Recently, on social media, various kinds of social engineering (SE) have made individuals more susceptible to attacks. A phishing attempt is a widely used SE technique that takes advantage of people’s vulnerabilities to acquire personal or confidential information. These attempts are growing at an astonishing speed, causing harm to both individuals and corporations. According to the latest studies, certain individuals are more vulnerable to such kinds of attacks than others. However, the relationship between psychological characteristics and phishing attacks has not been adequately investigated. This study empirically explores the connection between phishing vulnerability that causes data biases and the Big Five personality traits. Recognizing personality traits that make people more vulnerable to phishing attempts is a key step in developing protection and safeguarding individuals. The individuals who scored high in some traits are more probable to suffer from such assault. To the best of our knowledge, no prior quantitative study has attempted to find many genuine phishing victims and their personality behavior. This problem lacks the availability of publically accessible data. It is also challenging to estimate the probability distribution of rows in tabular data and generate realistic synthetic data to train/test the model on more data. This work employs a conditional generative adversarial network (C-GAN) for both data generation and classification to find the correlation between personality traits and phishing attacks.

Real-time strategy (RTS) games differ as they persist in varying scenarios and states. These games enable an integrated correspondence of non-player characters (NPCs) to appear as an autodidact in a dynamic environment, thereby resulting in a combined attack of NPCs on human-controlled character (HCC) with maximal damage. This research aims to empower NPCs with intelligent traits. Therefore, we instigate an assortment of ant colony optimization (ACO) with genetic algorithm (GA)-based approach to first-person shooter (FPS) game, i.e., Zombies Redemption (ZR). Eminent NPCs with best-fit genes are elected to spawn NPCs over generations and game levels as yielded by GA. Moreover, NPCs empower ACO to elect an optimal path with diverse incentives and less likelihood of getting shot. The proposed technique ZR is novel as it integrates ACO and GA in FPS games where NPC will use ACO to exploit and optimize its current strategy. GA will be used to share and explore strategy among NPCs. Moreover, it involves an elaboration of the mechanism of evolution through parameter utilization and updation over the generations. ZR is played by 450 players with varying levels having the evolving traits of NPCs and environmental constraints in order to accumulate experimental results. Results revealed improvement in NPCs performance as the game proceeds.

In December 2019, a pandemic named COVID-19 broke out in Wuhan, China, and in a few weeks, it spread to more than 200 countries worldwide. Every country infected with the disease started taking necessary measures to stop the spread and provide the best possible medical facilities to infected patients and take precautionary measures to control the spread. As the infection spread was exponential, there arose a need to model infection spread patterns to estimate the patient volume computationally. Such patients' estimation is the key to the necessary actions that local governments may take to counter the spread, control hospital load, and resource allocations. This article has used long short-term memory (LSTM) to predict the volume of COVID-19 patients in Pakistan. LSTM is a particular type of recurrent neural network (RNN) used for classification, prediction, and regression tasks. We have trained the RNN model on Covid-19 data (March 2020 to May 2020) of Pakistan and predict the Covid-19 Percentage of Positive Patients for June 2020. Finally, we have calculated the mean absolute percentage error (MAPE) to find the model's prediction effectiveness on different LSTM units, batch size, and epochs. Predicted patients are also compared with a prediction model for the same duration, and results revealed that the predicted patients' count of the proposed model is much closer to the actual patient count.

This article proposes a novel methodology to detect malicious uniform resource locators (URLs) using simulated expert (SE) and knowledge-base system (KBS). The proposed study not only efficiently detects known malicious URLs but also adapts countermeasure against the newly generated malicious URLs. Moreover, this article also explored which lexical features are contributing more in final decision using a factor analysis method, and thus help in avoiding the involvement of human experts. Furthermore, we apply the following state-of-the-art machine learning (ML) algorithms, i.e., naïve Bayes (NB), decision tree (DT), gradient boosted trees (GBT), generalized linear model (GLM), logistic regression (LR), deep learning (DL), and random rest (RF), and evaluate the performance of these algorithms on a large-scale real data set of data-driven Web applications. The experimental results clearly demonstrate the efficiency of NB in the proposed model as NB outperforms when compared to the rest of the aforementioned algorithms in terms of average minimum execution time (i.e., 3 s) and is able to accurately classify the 107 586 URLs with 0.2% error rate and 99.8% accuracy rate.

Law enforcement faces problems in tracing the true identity of offenders in cybercrime investigations. Most offenders mask their true identity, impersonate people of high authority, or use identity deception and obfuscation tactics to avoid detection and traceability. To address the problem of anonymity, authorship analysis is used to identify individuals by their writing styles without knowing their actual identities. Most authorship studies are dedicated to English due to its widespread use over the Internet, but recent cyber-attacks such as the distribution of Stuxnet indicate that Internet crimes are not limited to a certain community, language, culture, ideology, or ethnicity. To effectively investigate cybercrime and to address the problem of anonymity in online communication, there is a pressing need to study authorship analysis of languages such as Arabic, Chinese, Turkish, and so on. Arabic, the focus of this study, is the fourth most widely used language on the Internet. This study investigates authorship of Arabic discourse/text, especially tiny text, Twitter posts. We benchmark the performance of a profile-based approach that uses n -grams as features and compare it with state-of-the-art instance-based classification techniques. Then we adapt an event-visualization tool that is developed for English to accommodate both Arabic and English languages and visualize the result of the attribution evidence. In addition, we investigate the relative effect of the training set, the length of tweets, and the number of authors on authorship classification accuracy. Finally, we show that diacritics have an insignificant effect on the attribution process and part-of-speech tags are less effective than character-level and word-level n -grams.

We present a Conceptual Model for Software Fault Localization (CMSFL), and an Automated Assistant (AASFL) called BUG-DOCTOR to aid programmers with the problem of software fault localization. A multi-dimensional approach is suggested with both shallow and deep reasoning phases to enhance the probability of localizing many types of faults. BUG-DOCTOR uses these two approaches and switches between them to localize the faults. The AASFL is being developed based on this theoretical model. It is programming language independent, capable of handling different programming styles and implementations.

We are applying artificial intelligence techniques to develop a tool called BUG-DOCTOR that assists software engineers with program comprehension and debugging. In this paper we describe two of BUG-DOCTOR's knowledge sources, the Chunker and the Plan Processor. The Chunker identifies candidate chunks in the target code using program analysis techniques and a set of heuristics. Candidate chunks map to higher level concepts, and have a signature which captures their major identifying characteristics. The Plan Processor uses a signature to retrieve a set of program plans from a Plan Library with features that are similar to those of the candidate chunk. Its fuzzy reasoner then ranks the retrieved plans. The plan chosen as most similar to the candidate chunk is used for program comprehension and debugging tasks that follow. We believe that this approach could lead to more scalable tools for program comprehension and debugging.