Microsoft Technology Licensing, LLC

Dotan Patrich

Josef Weizman

Moshe Israel

Ram Haim Pliskin

Tomer Koren

Hani Hana Neuvirth

Yotam Livny

Idan Yehoshua Hen

Ben Kliger

Michael Zeev Bargury

Eran Goldstein

Aharon Naftali Michaels

Gueorgui Chkodrov

Elad Yom-Tov

Omer Karin

Tomer Teller

Dawn Antonette Burns

Jonathan Gazit

Mathias Scherman

Oran Brill

Yaakov Garyani

Vlad Korsunsky

Amit Magen Medina

Maya Maimon

Amit Magen

A computing system is configured for detecting anomalies in deployment configurations of container images at a container network. One or more datasets associated with deployment configurations of a container imager are collected, and a plurality of features are extracted based on the one or more datasets for an ID of the container image. A probability score is then generated based on the plurality of features, using a machine-learning model trained on datasets associated with historical deployment configurations of the container image that have been performed via the container orchestration service. The probability score indicates a probability of whether the deployment configurations of the container image are anomalous or not anomalous when compared historical deployment configurations of the container image. An allow list is generated that includes container images and their respective IDs that have a majority of their deployment configurations that are not anomalous.

Allow list of container images based on deployment configuration at a container orchestration service

Some embodiments bridge a gap between focusing on security alerts raised by conditions and events that have already occurred, and focusing on vulnerabilities that might be exploited in the future. Alerts are organized into alert categories, vulnerabilities are organized into vulnerability categories, and are optionally supplemented with misconfiguration categories. Correlations are identified between alert categories and vulnerability or misconfiguration categories, and the correlation values noted, to produce category association rules. The alerts, vulnerabilities, and other security findings are gathered in some situations from multiple similar environments, and in some cases are filtered to pertain to similar resources or similar configurations. The category association rules are utilized to perform cybersecurity prioritizations such as assigning priority levels to alerts and assigning likelihood levels to potential breaches. Graphs showing resources and data flow paths are annotated with risk scores or with security findings relevant to the applicable category association rules.

Security finding categories-based prioritization

A computing system is configured to detect a request for a deployment of a container at a container orchestration service. One or more datasets associated with the deployment of the container are collected, and a plurality of features associated with the deployment are extracted based on the one or more datasets. A probability score is then generated based on the plurality of features, using a machine-learning model trained on datasets associated with historical deployments of containers that have been performed via the container orchestration service. The probability score indicates a probability that the deployment of the container is anomalous compared to the historical deployments of containers. When the probability score is greater than a threshold, the deployment of the container is determined as anomalous.

Detect anomalous container deployment at a container orchestration service

According to examples, an apparatus may include a processor and a memory on which is stored machine-readable instructions that may cause the processor to identify a container image group of a plurality of container image groups to which a subject container image corresponds, in which each of the plurality of container image groups is assigned a respective behavioral profile. The processor may also determine whether activities in the subject container image comply with corresponding activities identified in the behavioral profile of the identified container image group. Based on a determination that at least one activity in the subject container image fails to comply with a corresponding at least one activity identified in the behavioral profile of the identified container image group, the processor may determine that the subject container image includes an anomalous activity and output an alert indicating that the subject container image includes an anomalous activity.

Anomalous activity detection in container images

Embodiments detect risky situations in which a domain name record remains viable after the target it identified is not. Such dangling records create various risks because substitute targets, such as fraudulent websites, may be installed without the knowledge of the original target's owner. By obtaining and correlating data from multiple tenants, a cloud service provider detects dangling structures and any attempts to exploit them. Dangling records may specify a custom domain name, for example, or a static IP address that can be misused. In response, the provider's security infrastructure can alert the original target's owner, block the attempted exploit, or otherwise mitigate the risks. Traffic monitoring, control plane API invocations, and domain name server queries may be employed by the security infrastructure to detect resource deletion, resource creation, and resource access attempts that correspond with vulnerable records or suspect activity involving them.

Dangling domain detection and access mitigation

Technologies are shown for detection of identity misconfiguration that involve collecting identity/role binding and role/access rules data from multiple clusters supported by a computing resource system. Access rules for identities are extracted from the collected data and an access rule prediction model created to predict access rules for identities. An identity definition request for a tenant is received having a requested identity and a role assigned to the identity. A set of access rules is obtained for the role assigned to the identity and a predicted set of access rules is obtained for the requested identity from the prediction model. The access rules for the requested role are compared to the predicted set of access rules and a misconfiguration alert generated when there is a difference between the set of access rules for the requested role and the predicted set of access rules for the requested identity.

Identity misconfiguration detection for role-based access control

Cybersecurity enhancements expose likely cyberattacks and command abuse while reducing false positives. Some embodiments ascertain an operating system mismatch, which occurs when a command tailored for operating system X is asserted in an environment tailored to operating system Y. False positives may be reduced by alerting on such a mismatch only when a command's process belongs to a web server or other targeted process, or uses the same supporting technology (e.g., framework, scripting language, or runtime environment) as the web server or other targeted process. Some embodiments watch for command abuse by spotting assertions of commands that appear frequently in cyberattacks even though those commands also have legitimate uses such as system administration, network administration, or software development.

Attack detection through exposure of command abuse

Performing anomaly lookup on data sources that include an entity related to an alert. One or more entities related to an alert and a date when the alert occurred are received. The alert may indicate that an anomaly in data collected from a various data sources may be present in at least one of the data sources. The various data sources are searched for the one or more entities around the alert date to determine which of the data sources include the one or more entities. For those data sources including the one or more entities, an anomaly lookup procedure is performed on the data sources during a first time window to determine an initial set of suspicious anomalies.

Anomaly lookup for cyber security hunting

The automated estimation that an interface service has been misconfigured. Sensitive interface services are first identified based on common characteristics, and those characteristics are associated with sensitivity based on behavior across multiple clusters. Thereafter, the threat assessment estimates that a particular interface service is misconfigured if the particular interface service has these same common characteristics, is accessible from outside the cluster, and does not require authentication. Cluster administrators can therefore be more fully and timely advised when a misconfiguration of an interface service subjects their cluster to undue security risks.

Interface threat assessment in multi-cluster system

'Sensitive' URIs for a website can be determined. Access attempts to a sensitive URI can be extracted from server logs. As used herein, sensitive URIs are URIs which if breached are likely to result in harm to the website owner. Access to sensitive URIs can be restricted to trusted accessors. Trusted accessors can be determined by filtering out untrusted accessors using thresholds and/or machine learning techniques. After filtering out untrusted accessors, any remaining accessors can be identified as trusted accessors. Trusted accessors can be added to a whitelist. Access requests to access-restricted URIs by an accessor not in the whitelist can be denied and an alert can be generated. Access requests to access-restricted URIs by an accessor in the whitelist can be granted.

Whitelisting of trusted accessors to restricted web pages

Systems, methods, and apparatuses are provided for restricting access to a web resource. Website access information is obtained by monitoring accesses to a plurality of websites for each access, which may include a network identifier of an access requestor, a website identifier, and an access time for each request. Based on at least the website access information, it may be determined that a particular access requestor has accessed a number of different websites in a given time period. As a result, the particular access requestor may be classified as a web robot. A request to permit access to a web resource is received by the particular access requestor. In response to receiving the request to permit access to the web resource, the particular access requestor is prevented from accessing the web resource and/or a notification is generated that the particular access requestor is attempting to access the web resource.

System and method for restricting access to web resources

Techniques are provided to dynamically generate response actions that may be used to investigate and respond to a security alert. Different prediction models are initially trained using a corpus of training data. This training data is obtained by identifying previous security alerts and then grouping together alert clusters. An analysis is performed to identify which steps were used to respond to the alerts in each group. These steps are fed into a prediction model to train the model. After multiple models are trained and after a new security alert is received, one model is selected to operate on the new alert, where the model is selected because it is identified as being most compatible with the new alert. When the selected model is applied to the new alert, the model generates a set of recommended steps that may be followed to investigate and/or respond to the new alert.

System and method to infer investigation steps for security alerts using crowd sourcing

Methods are provided for building and tuning a correlation data structure. The correlation data structure includes relationship correlations with relationship scores that reflect the level of correlation between alert conditions and feature set events that occurred in a machine. Each relationship correlation further includes a time of influence associated with the times of occurrence for each alert condition and corresponding feature set event. The correlation data structure is built and tuned using sourcing to leverage the alert conditions and feature set events on each machine for all machines in the network. Methods are also provided to use the correlation data structure to monitor the machines in a network, detect feature set events, and detect if alert conditions correlated with those feature set events are likely to occur. The methods further provide for mitigating those alert conditions.

Detection of attacks in the cloud by crowd sourcing security solutions

A computing system performs real-time mitigations for unfamiliar threat scenarios by identifying a particular threat scenario for a client system that has not previously experienced the threat scenario and for which a remediation process is unknown. The computing system responds to the unknown threat scenario by generating and providing the client system a mitigation file that includes a predictive set of mitigation processes for responding to the threat scenario. The mitigation file is generated by first generating a threat vector that identifies a plurality of different threat scenario characteristics for the particular threat scenario. Then, a classification model is applied to the threat vector to identify a predictive set of mitigation processes that are determined to be a best fit for the threat vector and that are included in the mitigation file.

Real-time mitigations for unfamiliar threat scenarios

A method includes obtaining a dictionary, data for a set of web requests, and definitions of a first set of clusters associated with vulnerability scanners. The method includes identifying a set of clients that transmitted the second set of web requests. The method includes generating a second set of feature vectors, which each corresponds to one of the clients. Each element in each feature vector corresponds respectively to an entry in the dictionary. The method includes clustering the second set of feature vectors into a second set of clusters. The method includes, in response to a first distance between a selected cluster of the second set of clusters and one of the first set of clusters being less than a first predetermined distance, (i) identifying one of the set of web services that received web requests corresponding to feature vectors in the selected cluster and (ii) generating a scanning alert.

Growing community of inventors

Rishon Lezion, Israel

Dotan Patrich