Next month, machine learning will put itself against top human hackers in the world’s first all-machine network defense tournament.
Top human hackers now have been met with challenges from machines. The Cyber Grand Challenge (CGC) seeks to automate this cyber defense process, using machine learning. The first generation of machines are tested to discover, prove and fix software flaws in real-time, without any assistance. If successful, the speed of autonomy could someday blunt the structural advantages of cyber offense.
Next month, seven machines will compete in the world’s first all-machine network defense tournament and the winner will compete against the world’ s top human hackers according to the Defense Advanced Research Projects Agency (DARPA)， the branch of the U.S. Department of Defense responsible for developing new technologies for the U.S. military.
With reams of data being generated and transferred over networks, cybersecurity experts will have a hard time monitoring everything that gets exchanged — potential threats can easily go unnoticed. Hiring more security experts would offer a temporary reprieve, but the cybersecurity industry is already dealing with a widening talent gap, and organizations and firms are hard-pressed to fill vacant security posts.
The solution might lie in machine learning, the phenomenon that is transforming an increasing number of industries and has become the buzzword in Silicon Valley. But while more and more jobs are being forfeited to robots and artificial intelligence, is it conceivable to convey to machines a responsibility as complicated as cybersecurity? The topic is being hotly debated by security professionals, with strong arguments on both ends of the spectrum. In the meantime, tech firms and security vendors are looking for ways to add this hot technology to their cybersecurity arsenal.
Simon Crosby, CTO at Bromium, calls machine learning the pipe dream of cybersecurity, in cybersecurity, you’re always up against some of the most devious minds, people who already know very well how machines and machine learning works and how to circumvent their capabilities. Many attacks are carried out through minuscule and inconspicuous steps, often concealed in the guise of legitimate requests and commands.
Others, like Mike Paquette, VP of Products at Prelert, argue that machine learning is cybersecurity’s answer to detecting advanced breaches, and it will shine in securing IT environments as they “grow increasingly complex” and “more data is being produced than the human brain has the capacity to monitor” and it becomes nearly impossible “to gauge whether activity is normal or malicious.”
What’s undeniably true is that machine learning has very distinct use cases in the realm of cybersecurity, and even if it’s not a perfect solution, it is helping improve the fight against cybercrime. MIT’s Computer Science and Artificial Intelligence Lab (CSAIL) has led one of the most notable efforts in this regard, developing a system called AI2, an adaptive cybersecurity platform that uses machine learning and the assistance of expert analysts to adapt and improve over time. The platform was tested during a 90-day period, crunching a daily dose of 40 million log lines generated from an e-commerce website. After the training, AI2 was able to detect 85% of the attacks without human assistance.
Humans and robots have no other choice than to unite against the ever-increasing threats that lurk in cyberspace.
The research wing of the U.S. military has announced that it will hold Cyber Grand Challenge a multiyear program that is set to culminate on Aug. 4 in Las Vegas at an unprecedented，open-to-the-public cyber defense competition to be held in collaboration with DEF CON, one of the world’ s largest and most venerable annual hacker conferences.
During the event，seven finalist teams’ programmers will step back and using machine learning, their machines will autonomously vie for millions of U.S. dollars in prizes. The team who wins the Cyber Grand Challenge will go on to pit its machine against the world’ s top human hackers in DEF CON “Capture the Flag” (CTF) competition on Aug. 5, according to DARPA.
“That would be the first-ever inclusion of a mechanical contestant in that event，and could presage the day when, as eventually happened with chess and Jeopardy, a computer proves to be the Grand Master of cyber defense” DARPA said in a statement.
A convincing demonstration that machine learning behind cyber defense is truly doable would be a major paradigm shift，and would speed the day when networked attackers no longer have the inherent advantage they enjoy today，” Walker said.