
As an Amazon Associate and affiliate partner, Menrva Books earns from qualifying purchases. Learn more
Many Malware detection systems these days are using signature based techniques to detect malwares and viruses. The zero day or new infected files are not detected by these signature based Anti Viruses and their signature is generated only after they have done their damage. Hence it becomes very important for a user to constantly update the antivirus software. To overcome these problems, we have proposed a solution based on Artificial Intelligence techniques. So the clients will not require frequent updates and probability of detecting zero day infections will rise abruptly. This project is based on implementing data mining algorithms mainly C4.5 Decision Tree learner. We have generated a dataset on the basis of already known malicious executable files. A C4.5 decision tree is generated based on the generated dataset and the unknown executables are passed through the tree to classify the executable as a malicious or a benign file. The purpose is to get rid of the manual signature based Malware detection systems that require constant updated signatures and making systems artificially immune to unknown and zero day malicious executables.
This book proposes an Artificial Intelligence-based solution to enhance malware detection capabilities beyond traditional signature-based methods. The authors address the limitations of current antivirus software, which often fail to detect zero-day or new infections until after damage has occurred, necessitating frequent updates. Their project implements data mining algorithms, specifically the C4.5 Decision Tree learner, to classify executable files as malicious or benign. By generating a dataset of known malicious files and building a decision tree, the system aims to provide artificial immunity against unknown threats without constant signature updates.
The authors present a technical approach to a persistent cybersecurity challenge, focusing on the practical application of AI and data mining techniques. The proposed solution aims to improve the detection rates of novel malware by leveraging machine learning algorithms, thereby reducing the dependency on frequent manual updates characteristic of traditional antivirus software. The methodology described suggests a systematic process for building and utilizing a decision tree for classification tasks within the cybersecurity domain. This work appears to be a focused study on a specific aspect of malware detection, offering a potential pathway toward more proactive and adaptive security systems.
Page Count:
76
Publication Date:
2011-08-01
Publisher:
Lap Lambert Academic Publishing GmbH KG
ISBN-10:
3845429992
ISBN-13:
9783845429991
No comments yet. Be the first to share your thoughts!