Enhancing Cyber security: Evaluating Machine Learning Algorithms for Effective Threat Detection and Classification
T. Anjamma, S. Yamuna Reddy · 2024
With the increasing frequency and complexity of cyber threats, enhancing cyber security measures has become imperative. Machine learning (ML) algorithms have shown promise in improving threat detection and classification by automating the identification of security incidents. This abstract presents a comprehensive evaluation of various ML algorithms for their effectiveness in cyber threat detection and classification. The evaluation is conducted using a diverse dataset encompassing different cyber attack scenarios and incorporating multiple features such as network traffic patterns, system logs, and user behavior. Key ML algorithms including decision trees, support vector machines, and neural networks are examined, and their performance is assessed using metrics like training accuracy and testing accuracy. The results highlight the efficacy of ML algorithms in accurately identifying and categorizing cyber threats. Additionally, the study investigates the impact of feature selection techniques and model optimization strategies on algorithm performance. The findings provide valuable insights into the strengths and limitations of each algorithm, enabling the practical implementation of robust threat detection and classification systems. This research contributes to the field of cyber security by facilitating the development of effective ML-based solutions, ultimately bolstering cyber defense mechanisms against evolving threats.