Virus signature detection algorithm

The purpose of this research is to develop an algorithm for finding virus signatures. The method of searching for virus signatures was analyzed to achieve this goal. A brief description of the Boyer-Moore algorithm was also considered. The result of the research is a new algorithm that optimizes the speed of finding virus signatures by scanning the beginning and end of the file, since these are common cases where viruses are located. The practical significance of this research lies in the development of an algorithm for finding virus signatures, which reduces the risk of infection of the operating system with viruses and provides the ability to quickly detect malware.

An Intrusion Detection System for Network Security Using Recurrent Neural Network

To maintain the security of vulnerable network is the most essential thing in network system; for network protection or to eliminate unauthorized access of internal as well as external connections, various architectures have been suggested. Various existing approaches has developed different approaches to detect suspicious attacks on victimized machines; nevertheless, an external user develops malicious behaviour and gains unauthorized access to victim machines via such a behaviour framework, referred to as malicious activity or Intruder. A variety of supervised machine algorithms and soft computing algorithms have been developed to distinguish events in real-time as well as synthetic network log data. On the benchmark data set, the NLSKDD most commonly used data set to identify the Intruder. In this paper, we suggest using machine learning algorithms to identify intruders. A signature detection and anomaly detection are two related techniques that have been suggested. In the experimental study, the Recurrent Neural Network (RNN) algorithm is demonstrated with different data sets, and the system’s output is demonstrated in a real-time network context.

Time Signature Detection: A Survey

This paper presents a thorough review of methods used in various research articles published in the field of time signature estimation and detection from 2003 to the present. The purpose of this review is to investigate the effectiveness of these methods and how they perform on different types of input signals (audio and MIDI). The results of the research have been divided into two categories: classical and deep learning techniques, and are summarized in order to make suggestions for future study. More than 110 publications from top journals and conferences written in English were reviewed, and each of the research selected was fully examined to demonstrate the feasibility of the approach used, the dataset, and accuracy obtained. Results of the studies analyzed show that, in general, the process of time signature estimation is a difficult one. However, the success of this research area could be an added advantage in a broader area of music genre classification using deep learning techniques. Suggestions for improved estimates and future research projects are also discussed.

A Lightweight Hybrid Detection Method for Botnet

Botnet is a serious threat for the Internet and it has created great damage to the Internet. How to detect botnet has become an ongoing endeavor research. Series of methods have been discussed in recent research. However, one of the remaining challenges is that the high computational overhead. In this paper, a lightweight hybrid botnet detection method is proposed. Considering the features in the botnet data packets and the characteristic of employing DGA (Domain Generation Algorithm) domain names to connect to the botnet, two sensors are designed and deployed individually and parallelly. Signature detection is used on the gateway sensor to dig out known bot software and deep learning based techniques are used on the DNS (Domain Name Server) server sensor to find DGA domain names. With this method, the computational overhead would be shared by the two sensors and experiments are conducted and the results indicate that the method is effective in detecting botnet

Sistem Absensi dan Monitoring Marketing Arteri Pondok Indah Divisi Used Car Menggunakan Metode Algoritma K-Nearest Neighbor dan Naive Bayes pada PT BCA Finance

INTISASI Di era globalisasi sekarang ini, seiring dengan semakin berkembangnya teknologi, banyak orang berharap agar segala sesuatu menjadi lebih praktis, saat ini dibutuhkan sistem untuk melakukan tracking yang mereka lakukan saat bekerja. Salah satu solusi dari masalah ini adalah adanya sistem monitoring terhadap sales dalam melakukan pekerjaannya dalam penjualan, sehingga di sini penulis akan menggunakan k-nearest neighbor dan Naive Bayesian sebagai metode untuk klasifikasi dalam proses absensi sales. Uji coba telah dilakukan untuk menguji fungsionalitas dari sistem yang dibuat. Pengujian akurasi untuk pendeteksi tanda tangan sebagai validasi dalam absensi dengan metode klasifikasi Naive Bayesian memberikan hasil dengan tingkat akurasi yang baik. Dengan sistem absen tanda tangan ini setiap sales tidak dapat melakukan absen jika data akun saat login tidak sesuai. GPS dapat digunakan untuk mengetahui posisi letak keberadaan sales dalam melakukan tracking pekerjaan yang akan di rekam setiap 10 menit sekali. Sistem tracing dengan GPS ini berfungsi untuk mengetahui posisi sales saat melakukan absen, istirahat, kembali bekerja, absen pulang, dan tracking per 10 menit. Kata Kunci : k-nearest neighbor, naive bayes, gps. ABSTRACT In today's era of globalization, along with the development of technology, many people hope that everything becomes more practical, now a system is needed to track what they do while working. One solution to this problem is the existence of a monitoring system for sales in doing their work in sales, so here the author will use k-nearest neighbor and Naive Bayesian as a method for classification in the sales attendance process. Trials have been carried out to test the functionality of the system created. Testing accuracy for signature detection as validation in attendance with the Naive Bayesian classification method gives results with a good level of accuracy. With this signature absent system, every salesperson cannot perform an absence if the account data at login does not match. GPS can be used to find out where the sales are in tracking jobs which will be recorded every 10 minutes. This tracing system with GPS functions to find out the position of sales when taking absences, resting, returning to work, absent from home, and tracking every 10 minutes. Keywords: k-nearest neighbor, naive bayes, gps.

Revealing and Sharing Malware Profile Using Malware Threat Intelligence Platform

Cyber Security is an interchange between attackers and defenders, a non-static balancing force. The increasing trend of novel security threats and security incidents, which does not seem to be stopping, prompts the need to add another line of security defences. This is because the risk management and risk detection has become virtually impossible due to the limited access towards user data and the variations of modern threat taxonomies. The traditional strategy of self-discovery and signature detection which has a static nature is now obsolete in facing threats of the new generation with a dynamic nature; threats which are resilient, complex, and evasive. Therefore, this thesis discusses the use of MISP and The Triad Investigation approach to share the Indicator of Compromise on Cyber Intelligence Sharing Platform to be able to address the newt threats.

The Impact of Ransomware on Individuals and Organizations in this Modern Era, Ways Forward

Ransomware is a severe security bottleneck and threat faced by individuals and organizations today in computer and information technology, and ransomware attacks are on the increase by the day. There is no infallible solution for protecting against Ransomware as the malware code uses metamorphic and polymorphic algorithms to generate different versions, thus evading signature detection. Ransomware also uses domain generator algorithms (DGA) to generate new domains for the command and control server (C&C), they constantly exploit new vulnerabilities, and they use various infection vectors. Thus, for an individual or organization to protect itself, an adaptive security architecture must constantly monitor the system to detect new ransomware infections at an early stage such that they block them before encryption of the files done. This approach is a defense in depth approach that supplements the network defenses such as patch management, anti-virus software, intrusion detection, firewalls, and content filtering. A framework for implementing the preempt and preventive security architecture model using open -source software was presented and the proposed framework is tested against the WannaCry and Petya Ransomware. The proposed framework was successfully able to alert of the ransomware attack and, it was even possible to prevent the Petya ransomware from executing on the victim host.