Computer systems and cyber-infrastructures will almost always be imperfect. This is why updates and patches are essential to these systems. But while the devs are busy creating the patches needed to fix the flaws of a computer system, malicious entities can sometimes take this time to launch a cyber attack to exploit the flaws. This type of cyber attack is called zero-day attacks, and this is the worst that could happen to vulnerable computer systems. Zero-day attacks…
can quickly overwhelm traditional defenses, resulting in billions of dollars of damage and requiring weeks of manual patching work to shore up the systems after the intrusion.
Computer scientists recognize the limitations of traditional defenses in computer systems, and so they try to make new types of computer security.
Now, a Penn State-led team of researchers used a machine learning approach, based on a technique known as reinforcement learning, to create an adaptive cyber defense against these attacks.
According to Minghui Zhu, associate professor of electrical engineering and computer science and Institute for Computational and Data Sciences co-hire, the team developed this adaptive machine learning-driven method to address current limitations in a method to detect and respond to cyber-attacks, called moving target defense, or MTD.
Learn more about this method over at TechXplore.
(Image Credit: TheDigitalArtist/ Pixabay)
Comments (1)