Abstract: A system and method for remediating cybersecurity events. A method includes querying a knowledge base using a query generated based on semantic concepts and entity-identifying values extracted from cybersecurity event data, wherein the knowledge base includes an entity graph having nodes representing respective entities, wherein the entities include software components of software infrastructure and event logic components of cybersecurity event logic deployed with respect to the software infrastructure; identifying at least one path in the entity graph based on results of the query, wherein each identified path is between one of the software components and one of the event logic components; identifying at least one root cause entity based on the identified at least one path; and performing at least one remedial action based on the identified at least one root cause entity.

Abstract: In an example, an apparatus comprises logic, at least partially including hardware logic, to implement a lossy compression algorithm which utilizes a data transform and quantization process to compress data in a convolutional neural network (CNN) layer.

Abstract: In an example, an apparatus comprises a plurality of execution units; and logic, at least partially including hardware logic, to determine a sub-graph of a network that can be executed in a frequency domain and apply computations in the sub-graph in the frequency domain. Other embodiments are also disclosed and claimed.

Abstract: Methods, apparatuses and computer program products implement embodiments of the present invention that include protecting a computing device by specifying one or more Internet sites that are accessible by one or more computing devices that communicate over a data network and identifying process binaries that executed on the computing devices accessed and retrieved data from any of the specified one more Internet sites. The identified process binaries are classified into a plurality of classes of matching process binaries, and for a given class, a count of the computing devices that that executed one of the process binaries of the given class is computed. When determining that the count of the computing devices is less than a predefined threshold, a preventive action is initiated to inhibit command and control (C2) channel transmissions from any of the computing devices that executed any of the process binaries of the given class.

Abstract: In an example, an apparatus comprises a plurality of execution units; and logic, at least partially including hardware logic, to determine a sub-graph of a network that can be executed in a frequency domain and apply computations in the sub-graph in the frequency domain. Other embodiments are also disclosed and claimed.

Abstract: In an example, an apparatus comprises a plurality of execution units comprising and logic, at least partially including hardware logic, to receive a plurality of data inputs for training a neural network, wherein the data inputs comprise training data and weights inputs; represent the data inputs in a first form; and represent the weight inputs in a second form. Other embodiments are also disclosed and claimed.

Abstract: In an example, an apparatus comprises a plurality of execution units comprising at least a first type of execution unit and a second type of execution unit and logic, at least partially including hardware logic, to expose embedded cast operations in at least one of a load instruction or a store instruction; determine a target precision level for the cast operations; and load the cast operations at the target precision level. Other embodiments are also disclosed and claimed.

Abstract: A mechanism is described for facilitating memory handling and data management in machine learning at autonomous machines. A method of embodiments, as described herein, includes detecting multiple tables associated with multiple neural networks at multiple autonomous machines, where each of the multiple tables include an index. The method may further include combining the multiple tables and multiple indexes associated with the multiple tables into a single table and a single index, respectively, where the single table is communicated to the multiple autonomous machines to allow simultaneous processing of one or more portions of the single table using one or more memory devices and one or more processors of one or more of the multiple autonomous machines.

Abstract: In an example, an apparatus comprises a plurality of execution units; and logic, at least partially including hardware logic, to determine a sub-graph of a network that can be executed in a frequency domain and apply computations in the sub-graph in the frequency domain. Other embodiments are also disclosed and claimed.

Abstract: In an example, an apparatus comprises a plurality of execution units comprising and logic, at least partially including hardware logic, to receive a plurality of data inputs for training a neural network, wherein the data inputs comprise training data and weights inputs; represent the data inputs in a first form; and represent the weight inputs in a second form. Other embodiments are also disclosed and claimed.

Abstract: Methods, apparatuses and computer program products implement embodiments of the present invention that include protecting a computing device by specifying one or more Internet sites that are accessible by one or more computing devices that communicate over a data network and identifying process binaries that executed on the computing devices accessed and retrieved data from any of the specified one more Internet sites. The identified process binaries are classified into a plurality of classes of matching process binaries, and for a given class, a count of the computing devices that that executed one of the process binaries of the given class is computed. When determining that the count of the computing devices is less than a predefined threshold, a preventive action is initiated to inhibit command and control (C2) channel transmissions from any of the computing devices that executed any of the process binaries of the given class.

Abstract: In an example, an apparatus comprises logic, at least partially including hardware logic, to implement a lossy compression algorithm which utilizes a data transform and quantization process to compress data in a convolutional neural network (CNN) layer. Other embodiments are also disclosed and claimed.

Abstract: In an example, an apparatus comprises a plurality of execution units comprising and logic, at least partially including hardware logic, to receive a plurality of data inputs for training a neural network, wherein the data inputs comprise training data and weights inputs; represent the data inputs in a first form; and represent the weight inputs in a second form. Other embodiments are also disclosed and claimed.

Abstract: In an example, an apparatus comprises a plurality of execution units comprising and logic, at least partially including hardware logic, to receive a plurality of data inputs for training a neural network, wherein the data inputs comprise training data and weights inputs; represent the data inputs in a first form; and represent the weight inputs in a second form. Other embodiments are also disclosed and claimed.

Abstract: A method and system for detecting vulnerable wireless devices operating in a wireless environment of an organization are provided. The method includes identifying a plurality of wireless devices operable in the wireless environment; for each identified wireless device: receiving intercepted traffic transmitted by the wireless device, wherein the intercepted traffic is transported using at least one type of wireless protocol; analyzing the intercepted traffic to determine if the wireless device is vulnerable, wherein the analysis is performed using an at least one investigation action; computing a risk score based on results of each of the least one investigation action; determining, based on the computed risk scores, if the wireless device is as vulnerable; and generating an alert, when it is determined that the wireless device is vulnerable.

Abstract: In an example, an apparatus comprises logic, at least partially including hardware logic, to save one or more outputs of a deep learning neural network in a storage system of an autonomous vehicle and upload the one or more outputs to a remote server. Other embodiments are also disclosed and claimed.

Abstract: In an example, an apparatus comprises a plurality of execution units comprising at least a first type of execution unit and a second type of execution unit and logic, at least partially including hardware logic, to expose embedded cast operations in at least one of a load instruction or a store instruction; determine a target precision level for the cast operations; and load the cast operations at the target precision level. Other embodiments are also disclosed and claimed.

Abstract: A mechanism is described for facilitating memory handling and data management in machine learning at autonomous machines. A method of embodiments, as described herein, includes detecting multiple tables associated with multiple neural networks at multiple autonomous machines, where each of the multiple tables include an index. The method may further include combining the multiple tables and multiple indexes associated with the multiple tables into a single table and a single index, respectively, where the single table is communicated to the multiple autonomous machines to allow simultaneous processing of one or more portions of the single table using one or more memory devices and one or more processors of one or more of the multiple autonomous machines.

Abstract: In an example, an apparatus comprises logic, at least partially including hardware logic, to implement a lossy compression algorithm which utilizes a data transform and quantization process to compress data in a convolutional neural network (CNN) layer. Other embodiments are also disclosed and claimed.

Abstract: In an example, an apparatus comprises a plurality of execution units; and logic, at least partially including hardware logic, to determine a sub-graph of a network that can be executed in a frequency domain and apply computations in the sub-graph in the frequency domain. Other embodiments are also disclosed and claimed.