Technology has taken a giant leap since the beginning of this century allowing thousands of concurrent transactions to be taken place over the web. Zillions of data is being transferred and received thanks to the development of cutting-edge technologies. While reams of data are being generated due to these transactions, the companies are having a hard time protecting them. Security companies are under constant pressure to develop and upgrade their technologies that can prevent the firms from malware attacks. That is why, stalwarts in e-learning like Intellipaat are providing focused learning on security aspects especially in areas like Data Science.
- About 230,000 computers got infected across 150 countries when WannaCry hit the windows based machines in May 2017
- The cost of damage incurred by cyber crime will reach up to $6 trillion per annum by 2021
- 99% of the computers are threat prone as the software like Java, Oracle, and Adobe which give full access to the hackers with just one click.
The funniest part is that these malware developers are equipped with advanced technologies and tools which the normal world has never heard of.
On one hand where Data Science and Artificial Intelligence is one of the most talked about term in the tech industry, the risk of ransomwares penetrating through the security walls of organizations has created severe threat. Artificial Intelligence is already in limelight for eating up the employment in future. However the question is, can artificial intelligence algorithms protect our data?
Popular Cyber attacks and malwares of 2017
MyDoom is considered to be the fastest and the most expensive virus which caused the damage costing $38.5 billion in Russia in the year 2004.
It has only been seven months and we are already being attacked by loads malwares from every direction possible. Ransomwares trapped the computer systems until the victims paid certain amount, on the other hand Android malwares kept polluting the cell phones based on that OS.
You definitely might have noticed a kind of pop-ups that advertise certain websites and tools and suddenly ask you to download an application. The moment you download that application, you IP address gets traced, and your data is doomed.
According to Heimdal Security, Social Media is the latest target of the cyber criminals.
You must have encountered with the phishing emails that ask you to provide you login credentials of any bank or ask your credit card number. All these and many more have affected many industries across the world making our security system vulnerable.
Machine Learning: The savior!
While the industries have still not managed to stand up after a huge loss caused by WannaCry malware, there is already a lot of talk going on about deploying machine learning to guard the systems. Machine learning, a field of Data Science that educates machines and helps them perform the tasks faster than humans. While human brain has intelligence to detect and analyze the patterns, machines have the capability to apply artificial intelligence models and perform the repetitive task at a stretch without intervention.
Though this is a brilliant idea but is it possible to get your machine ready for all the security possibilities? Machine Learning can be a proactive approach and defensive too. It can be educated to counter the probable security attacks and protect the system from potential security risks.
What measures can Machine Learning use?
Ultimately it comes to the Machine Learning experts, who are the main actors behind educating the machines. Digital signature, authentication, hiding the IP, masking identity, encryption, firewall, etc., have already been implemented by firms but what new can machine learning discover?
Deep machine learning can apply various algorithms to identify the malicious activities taking place on the network. It can be determined by finding unusual patterns interacting with the system infrastructure.
You might have seen Google asking you to verify if you are not a robot. You click on some of the images and then it lets you browse. When you browse Google for long hours, this is the common activity that happens. This way Google ensures that it is not a robot performing any malicious activities.
You can lock your mobile phone with your eye impressions that will keep your phone safe from unwanted access. You can also make sure if it is your voice commanding Siri to perform certain operations on your iPhone and not someone else’s.
MIT’s Computer Science and Artificial Intelligence Lab (CSAIL), has developed a cyber security system which is going to improve over time with the help of analysts who will add on the feedbacks in the system.
What can be the adversities of this solution?
The cyber criminals constantly create and upgrade applications finding the loophole of a particular system. Phishing mails, Trojan, eavesdropping, Denial of Service, etc., already exist in the market. However there are more malwares going to be developed and circulated about which the machine wouldn’t have knowledge or it will not be prepared for.
Though the idea of using intelligent machines for security purposes is a brilliant one, but educating the machines will probably impose some roadblocks on the way. Even if we go that far, it is going to take a lot of time to become that proficient. Machine learning is relatively a newer concept which has not matured yet. However it will be good to see the actual implementation of this concept.
Sonal Maheshwari has 6 years of corporate experience in various technology platforms such as Big Data, Data Science, Salesforce, Digital Marketing, CRM, SQL, JAVA, Oracle, etc. She has worked for MNCs like Wenger & Watson Inc, CMC LIMITED, EXL Services Ltd., and Cognizant. She is a technology nerd and loves contributing to various open platforms through blogging. She is currently in association with a leading professional training provider, Intellipaat Software Solutions and strives to provide knowledge to aspirants and professionals through personal blogs, research, and innovative ideas.