A method for training a machine learning model using information pertaining to characteristics of upload activity performed at one or more client devices includes generating first training input including (i) information identifying first amounts of data uploaded during a specified time interval for one or more of multiple application categories, and (ii) information identifying first locations external to a client device to which the first amounts of data are uploaded. The method includes generating a first target output that indicates whether the first amounts of data uploaded to the first locations correspond to malicious or non-malicious upload activity. The method includes providing the training data to train the machine learning model on (i) a set of training inputs including the first training input, and (ii) a set of target outputs including the first target output.

The present application describes a system that uses endpoint data and network data to detect an anomaly. Once an anomaly is detected, the system may determine a severity of the anomaly by comparing the anomaly to a global database of known anomalies. The system may then initiate preventative measures to address the anomaly.

A system for detecting and mitigating forged authentication object attacks is provided, comprising an authentication object inspector configured to observe a new authentication object generated by an identity provider, and retrieve the new authentication object; and a hashing engine configured to retrieve the new authentication object from the authentication object inspector, calculate a cryptographic hash for the new authentication object, and store the cryptographic hash for the new authentication object in a data store; wherein subsequent access requests accompanied by authentication objects are validated by comparing hashes for each authentication object to previous generated hashes.

An author of a malicious websites campaign (scam or phishing) likely uses a legitimate third-party service to facilitate the malicious campaign. An example includes legitimate CAPTCHA (Completely Automated Public Turing Test to Tell Computers and Humans Apart) services to conceal the malicious campaign from automated security scanners. A security service/platform can employ a detection pipeline that leverages use of CAPTCHA keys across websites of a malicious websites campaign. Websites that use CAPTCHA keys found in known malicious websites can at least be identified as suspect and communicated to firewalls.

A DNS server receives from a receiving email system, a DNS query for an email domain stored at the DNS server, the DNS query including identifying information of a sender of an email. The DNS server extracts the identifying information of the email sender from the DNS query and identifies one of a plurality of delivering organizations from the information. The DNS server determines whether the identified delivering organization is authorized to deliver email on behalf of the email domain. In response to determining that the identified delivering organization is authorized to deliver email on behalf of the email domain, the DNS server generates a target validation record based on the identity of the authorized delivering organization and the email domain, the target validation record including one or more rules indicating to the receiving email system whether the delivering organization is an authorized sender of email for the email domain.

Methods and systems for assessing internet exposure of a cloud-based workload are disclosed. A method comprises accessing at least one cloud provider API to determine a plurality of entities capable of routing traffic in a virtual cloud environment associated with a target account containing the workload, querying the at least one cloud provider API to determine at least one networking configuration of the entities, building a graph connecting the plurality of entities based on the networking configuration, accessing a data structure identifying services publicly accessible via the Internet and capable of serving as an internet proxy; integrating the identified services into the graph; traversing the graph to identify at least one source originating via the Internet and reaching the workload, and outputting a risk notification associated with the workload. Systems and computer-readable media implementing the above method are also disclosed.

A technique for detecting malware involves loading known malware information, finding a string in the known malware information, saving the string in a first database, identifying a first contiguous string block from the known malware information, assigning a confidence indicator to the first contiguous string block, attempting to find the first contiguous string block in a second database containing one or more contiguous string blocks extracted from known malware, and responsive to a determination the first contiguous string block meets a predetermined threshold of similarity with a second contiguous string block contained in the second database, labelling the first contiguous string block.

Methods, apparatus, systems and articles of manufacture are disclosed for classification of unknown samples using agglomerative clustering. An apparatus includes an extractor to extract a feature from a sample source code, the feature including at least one of a register, a variable, or a library based on a threshold of occurrence in a corpus of samples, the corpus of samples including malware samples, a dendrogram generator to generate a dendrogram based on features extracted from the sample source code, the dendrogram representing a collection of samples clustered based on similarity among the samples, the samples including sample clusters belonging to known malware families, and an anchor point identifier to traverse the dendrogram to identify similarity of an unknown sample to the sample clusters based on a confidence score, and identify anchor point samples from the sample clusters identified as similar to the unknown sample, the anchor point samples to provide metadata for use in extrapolating information to classify the unknown sample.

A collection apparatus that collects a URL of a Web page that leads to user operation and includes a search query generation unit that generates a search query by combining a digital content name and an associated keyword of the digital content. There is a fitness prediction unit that predicts a degree to which a Web page that leads to user operation is output as a search result when a search is performed by using the generated search query, a determination unit that searches for a Web page by using a search query in a search order that is based on the predicted degree, and determines analysis priority of a URL of a Web page on the basis of the degree and search result information. Further, there is a communication unit that outputs the URL of the retrieved Web page and the analysis priority of the URL.

Embodiments of the present disclosure provide systems, methods, and non-transitory computer storage media for identifying malicious enterprise behaviors within a large enterprise. At a high level, embodiments of the present disclosure identify sub-graphs of behaviors within an enterprise based on probabilistic and deterministic methods. For example, starting with the node or edge having the highest risk score, embodiments of the present disclosure iteratively crawl a list of neighbors associated with the nodes or edges to identify subsets of behaviors within an enterprise that indicate potentially malicious activity based on the risk scores of each connected node and edge. In another example, embodiments select a target node and traverse the connected nodes via edges until a root-cause condition is met. Based on the traversal, a sub-graph is identified indicating a malicious execution path of traversed nodes with associated insights indicating the meaning or activity of the node.