International Journal of Research in Engineering and Science (IJRES) ISSN (Online): 2320-9364, ISSN (Print): 2320-9356 www.ijres.org Volume 3 Issue 6 ǁ June 2015 ǁ PP.06-09 www.ijres.org 6 | Page Self Evolving Antivirus Based on Neuro-Fuzzy Inference System Prof. Sumedh Pundkar 1 , Pratik R. Upadhye 2 1 (Head Of Department of Computer Engineering Usha Mittal Institute of Technology, SNDT University, Mumbai, India) 2(Mukesh Patel School of Technology Management and Engineering, N.M.I.M.S. JVPD Scheme, Vile Parle, Mumbai, India) ABSTRACT: With today’s world filled with information and data, it is very important for one to know which information or data is harmless and which is harmful. Right from cellular phones to big MNCs and Server companies require a security system that is as competent and adaptive as its ever-updating and evolving viruses or malware. The paper talks about the development and implementation of a new idea Adaptive anti-virus based on Anfis logic. An adaptive anti-virus system that will catch up to the speed at which the viruses update and evolve. Keywords - Adaptive, Antivirus, Security, Neuro-Fuzzy, ANFIS, virus I. INTRODUCTION Adaptive antivirus based on Neuro-Fuzzy inference system can be a life time solution to the detrimental viruses and malware actions harming the health and the balance of the system. The primary limitation existing in all prevailing antivirus software security system is its lack of ability to detect new virus definitions at real time and more over it also requires human assistance and update-versions to make the Antivirus system able to detect and repair or block the newly discover viruses or malware. Thus we aim to develop and implement an Antivirus Security System that overcomes such limitations. This Antivirus security system will be self-adaptive and evolving software system that detects unusual behavior and registers these behaviour definition to get accustomed to it for future instances. It will neither need assistance from the developing team nor update- versions which would arrive when damage to the system may have already occurred. II. LITERATURE REVIEW The Literature review provides an overview of the various types of anti-virus techniques as mentioned in [1][2]. First-Generation Scanners Scanners of first-generation [3] typically looked for certain patterns or sequences of bytes called string signatures. Once a virus is detected, it can be analyzed precisely and a unique sequence of bytes extracted from the virus code. This string often called signature of the virus and is stored in the anti-virus scanner database. It must be selected such that not likely is appeared in benign programs or other viruses, optimistically. This technique uses this signature to detect the previously analyzed virus. It searches the files to find signatures of the viruses. It is one of the most basic and simplest methods employed by antivirus scanners. The anti-virus engine scans the binary code of files to find these strings; if it encounters with a known pattern, it alerts detection of the matching virus. Second-Generation Scanners The second-generation scanners [3] introduced exact and almost exact recognition that caused the antivirus scanners became more trustable. 2.1 Generic Detection “Generic detection” is a term applied when the scanner looks for a number of known variants, using a search string that can detect all of the variants[4]. While it may detect a currently unknown variant in which the same search string can be found, it’s only a heuristic detection if it involves the use of a scoring mechanism.Some systems use a hybrid approach, where a scoring system is added to the generic detection capabilities to give a probability of the variance or family membership with differing degrees of certainty. 2.2 Virus-specific Detection Sometimes the general virus detection algorithm may not be able to deal with a particular virus [5]. In such conditions, a virus specific detection algorithm must be developed to carry out detection procedure. Actually,