Ever since the pandemic began, the work from home culture took a sharp boost amongst the tech industries and so did the practice of laying off people, forcing more and more people to be bound at their homes with their machines and a lot of free time on their hands. This has led to a sharp spike in the pre-existing issues of mental health and other ill practices, thus forcing people to adapt a bit more destructive path such as performing cyber-attacks just for entertainments.
India alone experienced a 37% rise in cyber attacks in the First quarter of 2020 as compared to the last quarter of the previous year. A latest report by KSN showed that its products detected and blocked 52820874 from Jan to March of this year. India also ranks 27th worldwide in the number of web threats detected, India also ranks 11th worldwide in the number of attacks caused by servers that were hosted in the country, which accounts of 2,299,682 incidents in Q1 2020 as compared to 854,782 incidents detected in Q4 2019, said the report.
Apart from these the cyber-attacks on the government agencies has also increased exponentially aiming at a plethora of goals from defaming the agencies to straight away life endangering threats like exposing the nations important strategic data or deleting files concerning some major national project.
Advancements in Cyber Security Fields
Long gone are the days when the cyber experts had to analyse each and every entry manually for any possible suspect and defend the data bases with a few layers of security and some strong passwords.
The threat from cybercriminals is becoming increasingly sophisticated, so security needs to be able to adapt in order to keep up. Fortunately, there have been a number of recent technological developments that have helped improve the arsenal at our disposal to ensure we win the fight against cyber attacker. Technologies such as Internet of Things, Block chain, Stronger application security are helping us win this war.
Flaws in the current system
Even though these technologies give us a standing chance against the cyber threats out there, but even these do not ensure a concrete win against the attackers, as even these systems have a number of weak points such as, weak passwords which can be cracked even with a simple dictonary attack or a simple brute force attack, this is followed by the fact that majority of people are digitally illiterate and make them vulnerable to phishing attacks by a number of factors, Apart from these things the continuous evolution of cyber-criminals and their adaption to the latest technologies and tools makes it more difficult to keep track of their wrong doings. Lastly the ginormous improvement in the hardware technologies make it even difficult to keep up with these ill-intentioned people.
Advancements in Artificial Intelligence
The advancements in hardware technologies has helped in the improvement and implementation of artificial intelligence as well. In the recent years AI has evolved into an existent and practical thing from its theory roots. AI is being implemented in almost each and every domain and has been helping humanity for good till date (until Skynet takeovers the world).
With the use of extremely powerful machines and humongous datasets any and every things is being made possible, such as mundane tasks like suggesting what groceries to get to what performing lifesaving surgical operations. This potential of Artificial Intelligence can be harnessed, altered and polished to help us in the domain of cyber security as well.
Artificial Intelligence use cases in Cyber Security
In addition to AI’s potential for automation, there is also a great amount of interest in exploring the usage of AI to improve the current practice of cybersecurity.
Machine learning can detect and defend against intrusion, going beyond simple rule-based logic. For example, based on the factors such as access attempts, frequencies of queries, amount of data per query, outliers are automatically detected and flagged for suspicion.
Generally new malwares are created manually by sociopaths, but once that is done the further variants of the malware are autogenerated to evade detection. Enhancing traditional signature-based systems of malware detection with artificial intelligence can identify such future versions and variants of malware and prevent their spreading.
Discovery of code vulnerabilities
This is a relatively new field of implementation, where AI is used to scan vast amounts of code and identified any vulnerabilities
Fraudulent transactions and activity can be flagged and prevented in real-time by detecting patterns and identifying deviations from the expected baseline behavior. Anomaly detection, as this technique is commonly known, is one of the best-known applications of machine learning. Manually sifting through the vast amount of event logs to identify outliers is not only humanly impossible but is also best left to AI
The Flip side of the coin
AI as any other IT system comes with its own vulnerabilities. Attacks on AI systems mostly include, confusing the underlying model and bypassing what the AI system is supposed to do. For example , generative adversarial networks (GANs are a type of aritfical neural networks) can be used to fool a facial recognition security systems, these neural networks can also be implemented to disrupt speech applications and voice recognition systems too. Another example is that by fooling the AI system in a subtle way, a malware file may be made to be incorrectly classified as a safe file. As AI applications get more widely adopted, such risks will also increase. These risks first need to be understood before they can be mitigated. This also means that cybersecurity specialists need to have a very good understanding of how such applications work, what their susceptibility to adversarial attacks is, and how to become well-versed in machine learning technologies.
Weaponization of AI
Another major concern is the fact that AI is a double-edged sword and it can be manipulated to defy the very objective it was meant to protect. In the context of cybersecurity, we need to realize that the same AI technologies are also available to the malevolent actors and they are becoming adept at using AI and have started to employ them in a variety of ways. One such example is spear phishing, where emails are personalized using AI to maximize the chance of victims opening the emails and clicking through to unsafe links and sites. Not only that, hackers are also choosing their victims based on the likelihood of them “converting” — just like a regular marketer using AI.
AI can a really great ally in the war against cyber crimes but it also has to be controlled as it might be used by hackers to help them in their wrong doings, apart from this fact AI has to evolve further more for it to be reliable and be implemented in day to day life.
Special thanks to my team Ankitha Chate, Sankalp Chaudhary and Shaunak Deo for helping in the blog