Abstract:
Systems, apparatuses, methods, and computer readable mediums for modeling malicious behavior that occurs in the absence of users. A system trains an anomaly detection model using attributes associated with a first plurality of events representing system activity on one or more clean machines when users are not present. Next, the system utilizes the trained anomaly detection model to remove benign events from a second plurality of events captured from infected machines when users are not present. Then, the system utilizes malicious events, from the second plurality of events, to train a classifier. Next, the classifier identifies a first set of attributes which are able to predict if an event is caused by malware with a predictive power greater than a threshold.
Abstract:
The disclosed computer-implemented method for deploying applications included in application containers may include (1) identifying an application container that includes an application and facilitates transferring the application to a deployment environment, (2) performing a reconnaissance analysis on the deployment environment by identifying one or more properties of the deployment environment, (3) determining, based at least in part on the reconnaissance analysis, that the deployment environment meets a predetermined threshold of requirements for securely executing the application, and then (4) transferring the application included in the application container to the deployment environment in response to determining that the deployment environment meets the predetermined threshold. Various other methods, systems, and computer-readable media are also disclosed.
Abstract:
A computer-implemented method for enforcing data-loss-prevention policies using mobile sensors may include (1) detecting an attempt by a user to access sensitive data on a mobile computing device, (2) collecting, via at least one sensor of the mobile computing device, sensor data that indicates an environment in which the user is attempting to access the sensitive data, (3) determining, based at least in part on the sensor data, a privacy level of the environment, and (4) restricting, based at least in part on the privacy level of the environment, the attempt by the user to access the sensitive data according to a DLP policy. Various other methods, systems, and computer-readable media are also disclosed.
Abstract:
A computer-implemented method for enforcing data-loss-prevention policies using mobile sensors may include (1) detecting an attempt by a user to access sensitive data on a mobile computing device, (2) collecting, via at least one sensor of the mobile computing device, sensor data that indicates an environment in which the user is attempting to access the sensitive data, (3) determining, based at least in part on the sensor data, a privacy level of the environment, and (4) restricting, based at least in part on the privacy level of the environment, the attempt by the user to access the sensitive data according to a DLP policy. Various other methods, systems, and computer-readable media are also disclosed.
Abstract:
Decrypting network traffic on a middlebox device using a trusted execution environment (TEE). In one embodiment, a method may include loading a kernel application inside the TEE, loading a logic application outside the TEE, intercepting, by the logic application, encrypted network traffic, forwarding, from the logic application to the kernel application, the encrypted network traffic, decrypting, at the kernel application, the encrypted network traffic, inspecting, at the kernel application, the decrypted network traffic according to a sensitivity policy to determine whether the decrypted network traffic includes sensitive data, forwarding, from the kernel application to the logic application, filtered decrypted network traffic that excludes the sensitive data, processing, at the logic application, the filtered decrypted network traffic, forwarding, from the logic application to the kernel application, the filtered decrypted network traffic after the processing by the logic application, and forwarding, from the kernel application, the encrypted network traffic.
Abstract:
Decrypting network traffic on a middlebox device using a trusted execution environment (TEE). In one embodiment, a method may include loading a kernel application inside the TEE, loading a logic application outside the TEE, intercepting, by the logic application, encrypted network traffic, forwarding, from the logic application to the kernel application, the encrypted network traffic, decrypting, at the kernel application, the encrypted network traffic, inspecting, at the kernel application, the decrypted network traffic according to a sensitivity policy to determine whether the decrypted network traffic includes sensitive data, forwarding, from the kernel application to the logic application, filtered decrypted network traffic that excludes the sensitive data, processing, at the logic application, the filtered decrypted network traffic, forwarding, from the logic application to the kernel application, the filtered decrypted network traffic after the processing by the logic application, and forwarding, from the kernel application, the encrypted network traffic.
Abstract:
The disclosed method for assuring authenticity of electronic sensor data may include (i) capturing, using a sensor within a device, electronic sensor data, and (ii) digitally signing, using a cryptoprocessor embedded within the device, the electronic sensor data to create a digital signature that verifies that the signed electronic sensor data has not been modified since the electronic sensor data was captured by the sensor. Various other methods, systems, and computer-readable media are also disclosed.
Abstract:
The disclosed computer-implemented method for establishing restricted interfaces for database applications may include analyzing, by a computing device, query behavior of an application for query requests from the application to a remote database in a computer system and identifying, based on the analysis, an expected query behavior for the application. The method may include establishing, between the application and the remote database, a restricted interface. The method may include receiving, at the restricted interface, a query request from the application to the remote database and limiting, by the restricted interface, the query request from the application to the remote database based on the expected query behavior. The method may include determining, by checking the query request against the expected query behavior, that the query request is anomalous query behavior and performing a security action with respect to the computer system. Various other methods, systems, and computer-readable media are also disclosed.
Abstract:
A computer-implemented method for detecting malware-induced crashes may include (1) identifying, by analyzing a health log associated with a previously stable computing device, the occurrence of an unexpected stability problem on the previously stable computing device, (2) identifying, by analyzing an event log associated with the previously stable computing device, an event that is potentially responsible for the occurrence of the unexpected stability problem on the previously stable computing device, (3) determining, due at least in part to the event being potentially responsible for the occurrence of the unexpected stability problem on the previously stable computing device, that the event is potentially malicious, and (4) performing a security action in response to determining that the event is potentially malicious. Various other methods, systems, and computer-readable media are also disclosed.
Abstract:
The disclosed computer-implemented method for detecting malware using file clustering may include (1) identifying a file with an unknown reputation, (2) identifying at least one file with a known reputation that co-occurs with the unknown file, (3) identifying a malware classification assigned to the known file, (4) determining a probability that the unknown file is of the same classification as the known file, and (5) assigning, based on the probability that the unknown file is of the same classification as the known file, the classification of the known file to the unknown file. Various other methods, systems, and computer-readable media are also disclosed.