It appears that we’ll soon be able to detect malware hidden in short Twitter URLs courtesy of an intelligent system that’s being developed by a team of scientists with the support of the Engineering and Physical Sciences Research Council and the Economic and Social Research Council. The scientists decided to find a solution to this problem after analyzing a relatively successful Cardiff University study that managed to identify potential attacks within 5 seconds with an accuracy of 83%, while a 30-second window yielded a success rate of 93%. This test took place during the 2015 Superbowl and cricket world cup finals, and it analyzed the interaction between the user’s device and the destination website. If the device reported any unexpected changes such as altered files and processes, then the link in question was categorized as malicious.
Based on the gathered data, scientists were able to program their own system to identify attack signs and distinguish between safe and harmful URLs. The Director over at the Cardiff University Social Data Science Lab, Dr. Pete Burnap, explained why the team chose these important sporting events as their testing grounds.
“Unfortunately, the high volume of traffic around large scale events creates a perfect environment for cybercriminals to launch surreptitious attacks. It is well known that people use online social networks such as Twitter to find information about an event.”
The system will go through further testing during the European Football Championships next summer, and hopefully it will be used to make Twitter and other social media platforms safer in the near future. The CEO of EPSRC, Professor Philip Nelson, also had a few words to say about this project:
“Using social media is an integral part of modern life, vital to organisations, businesses and individuals. The UK needs to operate in a resilient and secure environment and this research will help combat these criminal cyberattacks.”
Thank you TheStack for providing us with this information.
