Phishing attacks are a form of social engineering that deceives users by imitating legitimate websites to steal sensitive information. This study focuses on phishing attacks tar geting local systems and introduces a newly developed attribute based dataset for detecting such attacks. The proposed dataset consists of 31 attributes derived from URL- and similarity based features. To assess the impact of feature engineering, three distinct datasets were generated, and their performance was compared across multiple classifiers. Several machine learning algorithms, including Decision Tree, Random Forest, Logistic Regression, Support Vector Machine, and Artificial Neural Network, are applied to evaluate classification performance. Experimental results demonstrate high accuracy in detecting phishing attacks on local systems, with the Logistic Regression method achieving the best result of 96.40%. Furthermore, validation on a publicly available dataset from Kaggle yielded an accuracy of 97.48%, confirming the model's strong generalization capability. These findings highlight the effectiveness of attribute-based datasets combined with machine learning approaches for improving phishing detection in real-world environments.

The use of social media has grown significantly, and businesses are now using these platforms to promote their products and services. To do this, companies have created business accounts on social networks. However, social media platforms can also be a breeding ground for unwanted behaviors such as cyberbullying, sexual content, and promotional comments. To address this issue, a study was conducted to create a system that could classify public accounts on Instagram by analyzing comments, profile pictures, bios, and posts shared by users with business accounts. First, a crawler was developed, and data were collected using this crawler and then anonymized. Next, the collected data were processed using natural language processing (NLP) techniques for text and image processing methods for images to extract features and create a dataset. Nearly 10 000 profiles and 30 000 comments from public accounts were manually tagged to create the classification model. The final model had an accuracy rate of 95% on the dataset, allowing for the effective identification of different types of business accounts on Instagram.