Schließen
Schließen
Ihr Netzwerk von morgen
Ihr Netzwerk von morgen
Planen Sie Ihren Weg zu einem schnelleren, sichereren und widerstandsfähigeren Netzwerk, das auf die von Ihnen unterstützten Anwendungen und Benutzer zugeschnitten ist.
          Erleben Sie Netskope
          Get Hands-on With the Netskope Platform
          Here's your chance to experience the Netskope One single-cloud platform first-hand. Sign up for self-paced, hands-on labs, join us for monthly live product demos, take a free test drive of Netskope Private Access, or join us for a live, instructor-led workshops.
            Ein führendes Unternehmen im Bereich SSE. Jetzt ein führender Anbieter von SASE.
            Ein führendes Unternehmen im Bereich SSE. Jetzt ein führender Anbieter von SASE.
            Netskope debütiert als Leader im Gartner ® Magic Quadrant ™ für Single-Vendor SASE
              Generative KI für Dummies sichern
              Generative KI für Dummies sichern
              Learn how your organization can balance the innovative potential of generative AI with robust data security practices.
                Modern data loss prevention (DLP) for Dummies eBook
                Moderne Data Loss Prevention (DLP) für Dummies
                Get tips and tricks for transitioning to a cloud-delivered DLP.
                  Modernes SD-WAN für SASE Dummies-Buch
                  Modern SD-WAN for SASE Dummies
                  Hören Sie auf, mit Ihrer Netzwerkarchitektur Schritt zu halten
                    Verstehen, wo die Risiken liegen
                    Advanced Analytics transforms the way security operations teams apply data-driven insights to implement better policies. With Advanced Analytics, you can identify trends, zero in on areas of concern and use the data to take action.
                        Die 6 überzeugendsten Anwendungsfälle für den vollständigen Ersatz älterer VPNs
                        Die 6 überzeugendsten Anwendungsfälle für den vollständigen Ersatz älterer VPNs
                        Netskope One Private Access is the only solution that allows you to retire your VPN for good.
                          Colgate-Palmolive schützt sein "geistiges Eigentum" mit intelligentem und anpassungsfähigem Datenschutz
                          Colgate-Palmolive schützt sein "geistiges Eigentum" mit intelligentem und anpassungsfähigem Datenschutz
                            Netskope GovCloud
                            Netskope erhält die FedRAMP High Authorization
                            Wählen Sie Netskope GovCloud, um die Transformation Ihrer Agentur zu beschleunigen.
                              Let's Do Great Things Together
                              Die partnerorientierte Markteinführungsstrategie von Netskope ermöglicht es unseren Partnern, ihr Wachstum und ihre Rentabilität zu maximieren und gleichzeitig die Unternehmenssicherheit an neue Anforderungen anzupassen.
                                Netskope solutions
                                Netskope Cloud Exchange
                                Netskope Cloud Exchange (CE) provides customers with powerful integration tools to leverage investments across their security posture.
                                  Technischer Support von Netskope
                                  Technischer Support von Netskope
                                  Überall auf der Welt sorgen unsere qualifizierten Support-Ingenieure mit verschiedensten Erfahrungen in den Bereichen Cloud-Sicherheit, Netzwerke, Virtualisierung, Content Delivery und Software-Entwicklung für zeitnahen und qualitativ hochwertigen technischen Support.
                                    Netskope-Video
                                    Netskope-Schulung
                                    Netskope-Schulungen helfen Ihnen, ein Experte für Cloud-Sicherheit zu werden. Wir sind hier, um Ihnen zu helfen, Ihre digitale Transformation abzusichern und das Beste aus Ihrer Cloud, dem Web und Ihren privaten Anwendungen zu machen.

                                      Detecting Ransomware Using Machine Learning

                                      Nov 23 2022

                                      Co-authored by Yihua Liao, Ari Azarafrooz, and Yi Zhang

                                      Ransomware attacks are on the rise. Many organizations have fallen victim to ransomware attacks. While there are different forms of ransomware, it typically involves the attacker breaching an organization’s network, encrypting a large amount of the organization’s files, which usually contain sensitive information, exfiltrating the encrypted files, and demanding a ransom. Therefore, a sudden increase of encrypted data movement in the corporate network traffic can be a strong indication of ransomware infection. To effectively detect such behavior patterns, at Netskope, we have developed the capability to detect encrypted files using machine learning (ML) and generate encrypted data movement alerts as part of Advanced UEBA (user and entity behavior analytics). This has helped our customers to identify ransomware attacks as they unfold in their network. One example is to detect ransomware on unmanaged devices. In this blog post, we will explain the technology behind encrypted file detection and Advanced UEBA, which is part of a pending patent application.  

                                      ML-based encrypted file detection

                                      The sequence of bytes in an encrypted file tends to be more random than unencrypted files, which is often manifested in some statistical measures of randomness and information density in the file. Therefore, these statistical tests can be helpful in determining whether a file is encrypted or not. We have explored various statistical tests, including:

                                      • Chi-square Test
                                      • Entropy
                                      • Arithmetic Mean
                                      • Monte Carlo Value for Pi
                                      • Serial Correlation Coefficient   

                                      However, our analysis shows that using any of these statistical tests alone is not sufficient to identify encrypted files and can generate excessive false positives. For example, some compressed files also look random according to some of these tests.

                                      To reduce the false positives from individual statistical tests, we developed a classification ML model to classify whether a file is encrypted or not. The model takes all of the statistical tests and other characteristics of the file as input features, based on millions of real and synthetic files of different file types. The model uses LightGBM, a decision tree-like ML algorithm, to automatically learn the difference between encrypted files and unencrypted files. In our experiments, the ML model was able to achieve good accuracy with low false positives.

                                      UEBA alerts

                                      The encrypted file classification ML model determines whether an individual file is encrypted or not. In a ransomware attack, there are usually hundreds or thousands of encrypted files involved. To further reduce false positives and help our customers identify the user accounts that were involved, we use Advanced UEBA to generate user-level alerts to flag users with anomalous encrypted data movements that are indicative of ransomware attacks.

                                      The goal of behavior analytics is to detect anomalous user behavior that indicates potential threats such as malicious insiders, compromised accounts, data exfiltration, ransomware, and other threats, through machine learning and statistical analysis. The figure below shows examples of ransomware detection policies in Advanced UEBA.

                                      In the case of ransomware attacks, an infected user may upload a large number of encrypted files to a managed cloud app. This can be deemed anomalous and highly unlikely when compared to the normal behavior profile of the same user, their peer groups, and all other users in the same organization. This is illustrated in the figure below. As a result, an UEBA alert is generated for this user.

                                      Netskope UEBA uses a scoring metric, User Confidence Index (UCI), to holistically evaluate the riskiness of users. The UCI Score helps security administrators easily identify the top risky users and take remediation actions based on the score. 

                                      UCI is calculated based on all the alerts associated with a user that occurred in the past, weighted by the severity and abnormality of the alerts, as well as the time decay factor. UCI ranges from 0 to 1000, the higher the score, the less risky the user. In the UCI dashboard, users are rank-ordered by the UCI score so that it’s easy for security administrators to view the riskiest users. As part of the adaptive access control feature, security administrators can configure policies based on the UCI score to block or alert the user’s access or activities. Below is an example of a user’s confidence score drop due to the ransomware infection, indicated by the uploads of encrypted files with ransomware extensions to a managed cloud app.

                                      Netskope’s Advanced UEBA has more than 100 detections for insiders, compromised accounts, and devices. As threat patterns change over time, we will add more detection capabilities to make Advanced UEBA more powerful. Please visit here to learn more about Netskope’s Advanced UEBA.

                                      author image
                                      Yihua Liao
                                      Dr. Yihua Liao is the Head of AI Labs at Netskope. His team develops cutting-edge AI/ML technology to tackle many challenging problems in cloud security.
                                      Dr. Yihua Liao is the Head of AI Labs at Netskope. His team develops cutting-edge AI/ML technology to tackle many challenging problems in cloud security.

                                      Bleiben Sie informiert!

                                      Abonnieren Sie den Netskope-Blog