Diverging deep learning cognitive computing techniques into cyber forensics

Area of Science:

• Cybersecurity
• Digital Forensics
• Artificial Intelligence

Background:

• Increasing cyber-attacks necessitate advanced methods for combating cybercrime.
• Digital forensic investigators face challenges analyzing large, complex datasets (Big Data) from diverse sources.
• Traditional methods struggle with the speed, volume, and complexity of data in modern cyber investigations.

Purpose of the Study:

• To propose a generic framework, the Deep Learning in Cyber Forensics (DLCF) Framework, for applying DL techniques to cyber forensics.
• To explore the potential of Deep Learning (DL), a subset of Artificial Intelligence (AI), in enhancing cybercrime investigations.
• To address the challenges faced by forensic investigators in handling Big Data for uncovering potential digital evidence (PDE).

Main Methods:

• The study focuses on the application of Deep Learning (DL) cognitive computing techniques.
• DL utilizes machine learning and neural networks that mimic human decision-making processes.
• A generic framework (DLCF) is proposed to integrate DL into cyber forensics workflows.

Main Results:

• Deep Learning (DL) demonstrates significant potential to transform cyber forensics.
• DL can assist in reducing bias within forensic investigations.
• DL may offer solutions for determining the admissibility of digital evidence in legal settings.

Conclusions:

• Deep Learning (DL) provides valuable tools for enhancing the fight against cybercrime.
• The proposed DLCF Framework can aid forensic investigators in managing and analyzing Big Data.
• DL holds the potential to significantly improve the efficiency and effectiveness of cyber forensic processes.