DDoS Attacks Detection using Naive Bayes Classifier
Deep Learning Model Moran Architecture for Text Recognition in Complex Images
Enhanced Intrusion Detection Framework: Integrating SMOTE-ENN with Random Forest and XGBoost
Resume Screening using NLP
Advancing User-Centric Privacy: A Comprehensive Research Roadmap for Ethical and Secure Technology Development
Internet usage has become essential for effective and timely communication, e-commerce activities, and financial transactions, contributing to a more sophisticated lifestyle. However, these activities are increasingly vulnerable to internet threats and fraud. A Distributed Denial of Service (DDoS) attack is a prevalent internet threat that disrupts the normal traffic of a victim server by overwhelming the target infrastructure with a flood of internet traffic. The primary aim of attackers is to create uncertainty for individuals or organizations, typically seeking financial gain or aiming to damage an organization's reputation. Notably, during the Russia-Ukraine war, significant DDoS attacks targeted Ukrainian bank servers to disrupt financial services for customers. This study employs the Naive Bayes model with 10-fold cross-validation to detect DDoS attacks. Naive Bayes, a widely recognized machine learning algorithm, demonstrated superior performance. The results revealed an average accuracy of 0.999, outperforming existing machine learning-based DDoS attack detection techniques.
Recognizing text in images poses significant challenges, particularly in the presence of complex backgrounds. This technology plays a crucial role in assisting visually impaired individuals and interpreting semantic content. This survey explores various techniques developed over the past decade to address text recognition in complex images. It provides an overview and analysis of accumulated works and evaluates the performance of these recognition methods. While image complexity is difficult to quantify, it can be described using parameters such as background details, noise levels, lighting conditions, textures, and fonts. Furthermore, the survey highlights several benchmark datasets employed in the reviewed studies. By examining these works, challenges in the field are identified and compared.
The growing sophistication of cyber-attacks necessitates advanced intrusion detection systems (IDS) capable of identifying both existing and emerging threats with high precision. This study proposes an innovative IDS framework that addresses class imbalance using SMOTE-ENN (Synthetic Minority Over-sampling Technique-Edited Nearest Neighbors), while leveraging the complementary strengths of Random Forest (RF) and XGBoost classifiers to enhance detection efficacy. Evaluated on the NSL-KDD dataset, the framework effectively mitigates the challenges posed by imbalanced data, ensuring improved detection of minority attack classes. Experimental analysis demonstrates significant improvements in accuracy, precision, recall, and F1-score compared to conventional methods. These findings highlight the framework's potential to strengthen cyber intrusion detection and enhance overall network defense mechanisms.
Resume screening is a critical step in the recruitment process, traditionally relying on manual review to assess candidates' qualifications. The advent of Natural Language Processing (NLP) has introduced advanced techniques to enhance this process by automating and optimizing resume evaluation. This paper explores the application of NLP in resume screening, focusing on methods such as keyword extraction, semantic analysis, and machine learning models. It discusses how NLP algorithms can identify relevant skills, experiences, and qualifications by analyzing the textual content of resumes. Furthermore, the integrating of NLP with applicant tracking systems (ATS) offers improved efficiency and accuracy in matching candidates to job requirements. The paper also examines challenges such as handling diverse resume formats and ensuring fairness in automated evaluations. By leveraging NLP, organizations can achieve a more streamlined and objective screening process, ultimately leading to better hiring outcomes and reduced bias in recruitment.
The User-Centric Privacy Development Framework serves as a vital guide for addressing privacy concerns in technological initiatives. It promotes user-centered design principles alongside proactive data privacy and security measures, enabling the creation of technology that respects and safeguards user privacy. By emphasizing evidence- based decision-making, the framework helps determine optimal data collection practices, including the appropriate volume of data, relevant metadata, and accurate measurement intervals. This structured methodology integrates user input to balance technological advancements with personal information protection, particularly in mobile technologies and data collection contexts. It provides comprehensive guidance to support innovation in privacy-centric technologies, fostering trust and confidence in their adoption. The framework highlights ethical principles and responsible data practices, aiming to enhance transparency, choice, and consent while minimizing the collection and disclosure of sensitive information. By building a culture of privacy respect, it offers valuable direction to practitioners, developers, and policymakers, ensuring adherence to user-centric privacy principles.
