Anomaly detection, the “identification of rare occurrences, items, or events of concern due to their differing characteristics from the majority of the processed data,” allows organizations to track “security errors, structural defects and even bank fraud,” according to DeepAI and described in three main forms of anomaly detection as: unsupervised, supervised and semi-supervised. Security Operations Center (SOC) analysts use each of these approaches to varying degrees of effectiveness in Cybersecurity applications.
On the surface, an “incremental stacking” approach to correlative analysis platforms like SIEM, XDR and UEBA is logical. Organizations can overcome some of the inherent limitations present in their security solutions by adding a network traffic analysis (NTA), for example. Industry analysts have been touting this approach for some time now as necessary for full coverage enterprise security.
A modern SOC should not be entirely dependent on human operators and their personal experience. The issue has been a foundational problem with not only the methodologies used by SOCs for the past 15 to 20 years, but it should be questioned whether the problem is actually compounded by the technology itself.
Since we determine everything on data here at MixMode, we went into our website data to see which of our Q2 articles got the most traffic over the past few months. Not surprisingly, the majority of our top articles covered topics on the advancement of AI in cybersecurity and network traffic analysis (NTA).
Yann LeCun and Yoshua Bengio were recently interviewed by VentureBeat Magazine on the topics of self-supervised learning and human-level intelligence for AI. Our CTO Dr. Igor Mezic sat down with our team to discuss some of the most interesting pieces of the LeCun article, and offer a potential solution to a search for truly self-supervised …
Our newest whitepaper, “How Predictive AI is Disrupting the Cybersecurity Industry,” evaluates several common SecOps issues around Network Traffic Analysis, explaining why typical solutions are wholly ineffective and represent sunk costs versus added value. We examine how self-supervised learning AI is poised to overcome the SecOps challenges of protecting today’s distributed networks.
For the past few years, a major problem has been mounting in the cybersecurity industry: a people shortage. Even before the outbreak of the current global pandemic, enterprises were hurting in the cybersecurity hiring department. Companies are struggling to find employable cybersecurity professionals to handle an ever increasing and evolving number of new threats from …
In today’s ever evolving cybersecurity landscape there are major problems facing professionals that continue to worsen. These problems center around a shortage of tools advanced enough to understand the baseline of a network in order to pinpoint anomalies and a massive information overload problem in the form of security alerts.
While it’s true that having a SIEM is better than forgoing network monitoring all together, a standalone SIEM solution is simply insufficient in today’s cybersecurity landscape. Hackers and other bad actors have become more sophisticated — many of today’s cybercriminals can easily outsmart a standard SIEM setup.