Micro Focus Lcc

Hewlett Packard Enterprise Development LP

Symantec Corporation

Hewlett-packard Development Company, L.p.

Pratyusa Kumar Manadhata

William G Horne

Martin Arlitt

Manish Marwah

Prasad V Rao

Tomas Sander

Stuart Haber

Mijung Kim

Sandeep N Bhatt

Barak Raz

Zulfikar Ramzan

Kent E Griffin

Amro J Awad

Kyle Williams

Tomasz Jaroslaw Bania

Mark Kevin Kennedy

Sandeep B Bhatkar

John Thomas Brassil

Miranda Jane Felicity Mowbray

Alexander Ulanov

Renato Keshet

Jun Li

Geoffrey Ndu

Tzi-cker Chiueh

Darrell Kienzle

Matthew Elder

Adrian Shaw

Christopher Ian Dalton

Christopher L Dalton

Ryan Kumar Persaud

Brent James Miller

Sandeep Yadav

Marc R Eisenbarth

Muhammad Ihsanulhaq Sarfraz

Amruta Gokhale

William G Home

Loai Zomlot

Liu Yang

Ravi Arun Netravali

A service receives, from client computing devices of client networks, information regarding incoming network traffic addressed to dark Internet Protocol (IP) address spaces the of client networks. The service can predict a cyber attack based on the information received from the client computing devices of the client networks. The server computing device notifies the client computing device of each client network affected by the predicted cyber attack.

Cyber attack prediction based on dark IP address space network traffic to plural client networks

In some examples, a system balances a number of positive data points and a number of negative data points, to produce a balanced training data set, where the positive data points comprise features associated with authentication events that are positive with respect to an unauthorized classification, and the negative data points comprise features associated with authentication events that are negative with respect to the unauthorized classification. The system trains a plurality of models using the balanced training data set, wherein the plurality of models are trained according to respective different machine learning techniques. The system selects a model from the trained plurality of models based on relative performance of the plurality of models.

Training models based on balanced training data sets

Techniques and apparatuses are described to enable a strategically coordinated fictitious ecosystem of disinformation for cyber threat intelligence collection in a computing network. The ecosystem comprises fictitious profiles and supporting fictitious infrastructure information to portray in-depth, apparent authenticity of the ecosystem. Malicious communications from an adversary directed at the ecosystem are monitored, and threat intelligence about the adversary is collected to prevent future attacks.

Disinformation ecosystem for cyber threat intelligence collection

A machine-readable medium may store instructions executable by a processing resource to access log data of an enterprise and extract time-series data of an enterprise entity from the log data. The time-series data may include measured feature values of a set of selected features over a series of time periods. The instructions may be further executable to train a predictive model specific to the enterprise entity using the time-series data, wherein the predictive model is to generate, for a particular time period, a predicted feature value for each of the selected features; access actual feature values of the enterprise entity for the particular time period; apply first-level deviation criteria to the actual feature value and the predicted feature value of each selected feature to identify deviant features of the enterprise entity; and apply second-level deviation criteria to the identified deviant features to identify the enterprise entity as behaving abnormally.

Abnormal behavior detection of enterprise entities using time-series data

In some examples, a Domain Name System (DNS) server receives, over a network, DNS queries containing domain names, extracts a common domain name shared by the domain names, determines whether a measure of an amount of data relating to the DNS queries containing the common domain name exceeds a threshold, and in response to determining that the measure of the amount of data relating to the DNS queries containing the common domain name exceeds the threshold, trigger a countermeasure action to address a threat associated with the DNS queries.

Defending against domain name system based attacks

For each of a number of naming deviation types, the number of deviations within a domain name of a domain is determined. Each naming deviation type is a different type of deviation from domain name naming rules. For each naming deviation type for which the number of deviations is non-zero, first benign and malicious probabilities that benign and malicious domains, respectively, have the naming deviation type are estimated. Second benign and malicious probabilities that any given domain is respectively benign and malicious are estimated. Probabilities that the domain is benign and malicious are estimated based on the number of deviations for each naming deviation type and based on the estimated first and second benign and malicious probabilities. Whether the domain is benign or malicious is determined based on the estimated probabilities that the domain is benign and malicious.

Determining whether domain is benign or malicious

In some examples, a plurality of alerts relating to issues in a computing arrangement are received, where the plurality of alerts generated based on events in the computing arrangement. A subset of the plurality of alerts is grouped into a bundle of alerts, the grouping being based on a criterion. The bundle of alerts is communicated to cause processing of the alerts in the bundle of alerts together.

Grouping alerts into bundles of alerts

In some examples, an alert relating to an issue in a computing arrangement is received. It is determined that the received alert is similar to a given alert in an information repository containing information of past processes performed to address respective issues, the determining comprising comparing a property associated with the received alert to a property of alerts associated with the past processes, and the information contained in the information repository comprising actions taken in the past processes to address the respective issues. Performance of a remediation action is triggered that comprises an action, identified by the information in the information repository, taken to respond to the given alert.

Responding to alerts

A technique includes determining relations among a plurality of entities that are associated with a computer system; and selectively grouping behavior anomalies that are exhibited by the plurality of entities into collections based at least in part on the determined relations among the entities. The technique includes selectively reporting the collections to a security operations center.

Reporting behavior anomalies

Example embodiments disclosed herein relate to propagating belief information about malicious and benign nodes. In one example, a domain name system (DNS) resolution graph including multiple nodes is determined. In this example, a first subset of nodes is determined based on an initial benign value or an initial unknown value associated with the respective nodes. In the example, benign belief information is propagated for the first subset based on the respective initial benign values. Moreover, in the example, a second subset of the nodes is determined based on an initial malicious value or an initial unknown value. Malicious belief information is propagated for the second subset based on the respective malicious values. The propagated belief information is copied to a DNS resolution graph.

Propagating belief information about malicious and benign nodes

In some examples, a system identifies, for a given authentication event between a plurality of devices in a network, a context comprising a set of authentication events that are temporally related to the given authentication event. The set of authentication events occur at the devices. A classifier is applied on a collection of features associated with the set of authentication events, the collection of features comprising a number of machines or a number of users associated with the set of authentication events. The system determines, based on an output of the classifier, whether the given authentication event is an unauthorized authentication event.

Unauthorized authentication event detection

Systems and methods for identifying, in a domain name, n-grams that do not appear in words of a given language, where n is greater than two are disclosed. The disclosed systems and methods may include comparing a value based on a number of the identified n-grams to a threshold and indicating that the domain name is potentially generated by malware in response to the value having a specified relationship with respect to the threshold.

Indicating malware generated domain names using n-grams

Updating ground truth data in a security management platform is disclosed. One example is a system including at least one processor and a memory storing instructions executable by the at least one processor to receive, in a security management platform, event data relating to a plurality of events corresponding to operation of a computing arrangement in a current time interval, and computing ground truth data for the current time interval based on the received event data, and threat intelligence data from time intervals preceding the current time interval. A prediction model is applied to generate predictions for the current time interval based on the received event data. Ground truth data is re-computed for the time intervals preceding the current time interval based on a comparison of the generated predictions and the computed ground truth data.

Updating ground truth data in a security management platform

In some examples, for a given authentication event between a plurality of devices in a network, a system identifies a set of events, at the devices, that are temporally related to the given authentication event. The system applies a classifier on a collection of features associated with the set of events, and determines, based on an output of the classifier, whether the given authentication event is an unauthorized authentication event.

Unauthorized authentication events

In some examples, a system counts a number of digits in a domain name. The system compares a value based on the number of digits to a threshold, and indicates that the domain name is potentially generated by malware in response to the value having a specified relationship with respect to the threshold.

Growing community of inventors

Piscataway, NJ, United States of America

Pratyusa Kumar Manadhata