LightCyber develops automated behavioral analytics capabilities, using sophisticated machine learning to quickly, efficiently and accurately identify attacks based on identifying behavioral anomalies inside the network.
“The LightCyber team’s vision to bring automation and machine learning to bear in addressing the very difficult task of identifying otherwise undetected and often very sophisticated attacks inside the network is well-aligned with our platform approach,” said Mark McLaughlin, Chairman and CEO, Palo Alto Networks.
“This technology will complement the existing automated threat prevention capabilities of our platform to help organizations not only improve but also scale their security protections to prevent cyber breaches,” explained McLaughlin.
Bringing behavioral analytics to the platform will enhance Palo Alto Networks’ automated threat prevention capabilities and the ability for customer organizations to prevent cyber breaches throughout the entire attack life cycle.
“Palo Alto Networks has been driving a paradigm shift in the security industry with its natively engineered and highly automated Next-Generation Security Platform designed to change the equation in how organizations prevent cyber breaches. We are pleased to join the Palo Alto Networks team, combining our technology innovations and accelerating adoption of behavioral analytics to help organizations bolster their defenses against the advanced and sophisticated adversaries they are facing today,” said Gonen Fink, CEO, LightCyber.
Automated attack behavior analytics enhances breach prevention
According to a report by the Ponemon Institute, when attackers successfully find their way into a network, there is an industry average dwell time of approximately five months to discover their activity. During that time, an advanced attacker can initiate command and control, lateral movement, and data exfiltration. This kind of dwell time and advancement in the attack lifecycle can lead to extensive damage and loss of confidential data.
Palo Alto Networks explains that common approaches to this problem include third-party, log-based collection and analysis tools that are often error-prone, limited in visibility, lack important context, are labor-intensive, require a data scientist to investigate false positives and tune for accurate outcomes, and lack enforcement capabilities.
To address these challenges, reduce attacker dwell time, minimize damage done and prevent breaches, the LightCyber technology claims to employ highly accurate and automated machine learning techniques to analyze user and entity activity and then identifies and protects against anomalous activities that are indicative of an active attack.
It further claims that the behavioral attack detection capability complements its existing protections delivered by the Palo Alto Networks platform to help security team members focus on only the most meaningful alerts and improve the time to breach response and prevention.
