دانلود گزارش تجزیه و تحلیل داده های بزرگ و سیستم های هوشمند برای هوش تهدید سایبری

The cybersecurity community is slowly leveraging machine learning (ML) to combat ever-evolving threats. One of the biggest drivers for the successful adoption of these models is how well domain experts and users can understand and trust their functionality. Most models are perceived as a black box despite the growing popularity of machine learning models in cybersecurity applications (e.g., an intrusion detection system (IDS)). As these black-box models are employed to make meaningful predictions, the stakeholders’ demand for transparency and explainability increases. Explanations supporting the output of ML models are crucial in cybersecurity, where experts require far more information from the model than a simple binary output for their analysis.

In addition, most of the detected intrusions provide a limited set of attributes on a single phase of an attack. Accurate and timely knowledge of all stages of an intrusion would allow us to support our cyber-detection and prevention capabilities, enhance our information on cyber threats, and facilitate the immediate sharing of information on threats, as we share several elements. Big data analytics is an umbrella term for multidisciplinary methods of data analytics that employ advanced mathematical and statistical techniques to analyze large datasets. While data science is a powerful tool to enhance performance, it is only as strong as the data used to develop the solutions. Big data analytics is the intelligence brought to data to transform data into actionable insights for industry and society. Big data analytics benefits organizations in many ways, driving competitiveness and innovation.