This study presents an innovative approach to darknet traffic classification, combining advanced machine learning techniques with hybrid LASSO-random forest (HLRF) feature selection and IP geolocation mapping. We propose a new ensemble model that significantly outperforms traditional classifiers, achieving an accuracy of 96.86% and an F1-score of 96.12%. Our research utilises an enhanced version of the CIC-Darknet2020 dataset, augmented with additional darknet traffic collected over a six-month period. The HLRF selector is employed to identify the most relevant features, improving the model's efficiency and interpretability. Furthermore, we incorporate IP geolocation mapping to provide insights into the global distribution of darknet activities. Our findings demonstrate the effectiveness of our ensemble method with HLRF feature selection in capturing complex darknet traffic patterns and highlight the challenges in geographical attribution due to sophisticated anonymisation techniques. This work contributes to the field of cybersecurity by offering an improved method for darknet traffic classification and providing a deeper understanding of the global nature of darknet operations.

Smartphone usage has increased in the recent past and has become an extension of the personal computer, so has the complexity of forensic investigation. Vital information on these devices makes them more critical especially when it is part of investigative evidences. The challenge here is the extraction of data, especially when the phone is logically or physically damaged. Chip-off is a niche technique, involving removal of Flash Memory chip with due sophistication, this then is subjected to direct extraction and analysis. Apple iPhones are robust and well locked; the study performed chip-off on model A1203 that revealed vital forensic evidences.