SYSTEM FOR DETECTING MALWARE USING DEEP LEARNING

Abstract

The present invention relates to a system and method for detecting malware using deep learning techniques, integrating both static and dynamic analysis to identify known and unknown malware threats in real time. The system continuously monitors system activities, network traffic, and software behaviors, extracting relevant features for deep learning models such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). By analyzing both code structure and runtime behaviors, the system accurately classifies software as benign or malicious, improving detection rates and reducing false positives. The invention provides enhanced protection against sophisticated malware in diverse computing environments, from individual devices to large-scale network infrastructures.

Specification

Description:The present invention relates to cybersecurity and, more specifically, to a system and method for detecting malware using deep learning techniques. The invention provides an automated solution for identifying and mitigating malware threats by analyzing both static and dynamic characteristics of software through deep learning models, such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), in real-time computing environments.
BACKGROUND OF THE INVENTION
The following description of related art is intended to provide background information pertaining to the field of the disclosure. This section may include certain aspects of the art that may be related to various features of the present disclosure. However, it should be appreciated that this section be used only to enhance the understanding of the reader with respect to the present disclosure, and not as admissions of prior art.

The rapid evolution of malicious software, or malware, presents significant challenges for traditional dete , Claims:1. A system for detecting malware in a computing environment, comprising:
• A malware detection module configured to monitor system activities, network traffic, and file behaviors in real-time;
• A feature extraction unit configured to extract features from at least one of static and dynamic analysis of software, including file attributes and runtime behaviors;
• A deep learning engine configured to process the extracted features and classify the software as either benign or malicious based on learned patterns.

2. The system of claim 1, wherein the deep learning engine is a convolutional neural network (CNN).

3. The system of claim 1, wherein the deep learning engine is a recurrent neural network (RNN).

4. A method for detecting malware in a computing environment, comprising:
• Monitoring system activities, network traffic, and file behaviors in real-time;
• Extracting features from both static and dynamic sources of software, including code structure and runtime behavior;
• Feeding the extracted features

Documents