Let’s separate the hype from reality and see what exactly machine learning (ML), deep learning (DL) and artificial intelligence (AI) algorithms can do right now in cybersecurity. We will look how different tasks, such as prediction, classification, clustering and recommendation, are applicable to the ones for attackers, such as captcha bypass and phishing, and for defenders, such as anomaly detection and attack protection. Speaking about the icing on the cake, we will cover the latest techniques of hacking security and non-security products that use ML and why its super hard to protect them against adversarial examples and other attacks.
