Abstract: Techniques for enhancing the editability of generated vector graphics are provided. In an example method, a processing device receives an image. The method further includes determining one or more regions of the image. The method further includes classifying each region as a stroke or a fill by determining a characteristic axis of the region. The method further includes generating a spatial data structure representing the regions classified as strokes using a characteristic axis of each stroke. The method further includes determining pairs of overlapping strokes and fills. The method further includes identifying, using the pairs of overlapping strokes and fills and the spatial data structure, at least one associated stroke-fill pair. The method further includes determining a layer ordering of the at least one associated stroke-fill pair. The method further includes generating a vector graphic using the at least one associated stroke-fill pair according to the layer ordering.

Abstract: Agents are installed across a set of clients to collect values for a set of features associated with files backed up from the clients to a data protection appliance. Each file is classified as being one of included or excluded based on the collected data. Files classified as included are allowed to remain at the appliance. Files classified as excluded are moved from the appliance to cloud storage. A machine learning model is trained using the collected data. The machine learning model is applied to classify a new set of files.

Abstract: An AI-driven indexing framework for probe-based backup systems that enables intuitive, context-aware search and real-time metadata categorization using natural language processing (NLP) to improve accessibility and simplify searches in a distributed system. An adaptive indexing system optimizes searches in the system by dynamically re-indexing files based on real-time access patterns, ensuring faster file retrieval and user-friendly interaction. A feedback loop provides continuous improvement by continuously collecting data about access trends and system usage behavior, and modifying the index using the collected data to adapt the indexing to changing data patterns.

Abstract: An AI-driven resource hotspot detection method identifying bottlenecks for application execution in a distributed network. A telemetry data collector receives real-time telemetry data from resources and applications of the distributed network, and extracts resource utilization features. An AI-driven telemetry analysis component detects trends in resource usage from the resource utilization features, and performs pattern analysis of the detected trends to predict future resource bottlenecks as predictions. A natural language summary and actionable recommendations for bottleneck minimization are generated based on the predictions, and provided to the user. A service request support ticket can be automatically generated.

Abstract: An AI-driven indexing framework for probe-based backup systems that enables intuitive, context-aware search and real-time metadata categorization using natural language processing (NLP) to improve accessibility and simplify searches in a distributed system. An adaptive indexing system optimizes searches in the system by dynamically re-indexing files based on real-time access patterns, ensuring faster file retrieval and user-friendly interaction. A feedback loop provides continuous improvement and an integrated anomaly detection mechanism proactively identifies and resolves indexing issues such as data corruption or unauthorized access, ensuring accurate and reliable data recovery.

Abstract: The technologies described herein are generally directed to using machine learning to allocate auxiliary data collection resources. For instance, a system can identify an anomaly in operation of a computing node of computing nodes of a network. The system may further identify, by employing a machine learning model, respective locations of telemetry information representative of operations of computing nodes that have dependencies upon the computing node, with the machine learning model being trained based on data representative of past anomalies in computing nodes of the network. Further, the system may, based on the telemetry information, identify and direct a network failure mitigation resource to perform a mitigation action to mitigate effects of the anomaly.

Abstract: The technologies described herein are generally directed to managing a network using multi-agent, adaptive machine learning. For instance, a system can, based on a performance objective of a geographic area, a global policy model resulting in model training data. The example system may further include communicating the model training data to a base station of the base stations of the geographic area. The example system may further include, receiving from the base station, a model gradient value applicable to modifying the global policy model, with the model gradient value being identified based on an action implemented by the base station that was selected based on a base station maintained by the base station, that was trained based on the model training data and a local performance objective applicable to the base station.

Abstract: The technologies described herein are generally directed to using machine learning to prioritize wireless reassociation. For instance, a system can identify state information corresponding to a candidate computing device of a network, wherein the candidate computing device is hosting a candidate communication session to be handed over from a first access point of the network. The system may further, based on the state information, change, employing a machine learning model, a handover priority score of the candidate communication session, wherein the machine learning model was trained based on data representative of past network events in past communication sessions of the computing devices of the network, resulting in a changed handover priority score. The system may further, based on the changed handover priority score, cause a handover of the candidate communication session from the first access point to a second access point of the network.

Abstract: The technologies described herein are generally directed to using machine learning to identify, analyze, and select storage resources for auxiliary data associated with a system event. For instance, a system can identify a network event in an operation of a computing node of a network. The example method may further include identifying, by employing a machine learning model, respective auxiliary data including respective sources of auxiliary data representative of operations of dependent computing nodes of the computing nodes, different from the computing node, that have dependencies upon the operation of the computing node. In the example method, the machine learning model was trained based on data representative of past network events. The example method may further include, based on the respective classifications of the respective auxiliary data, facilitating, by the computing system, storage of the respective auxiliary data at a storage location of a hierarchical storage system.

Abstract: Autonomous metadata harmonization in multi-cloud environments (e.g., using a computerized tool), is enabled. For example, a corresponding process can comprise validating, using a local artificial intelligence model that was trained using federated learning applied to a group of zones of a multi-cloud architecture, a metadata attribute in a zone of the group of zones of the multi-cloud architecture, in response to determining a deviation in the metadata attribute, determining a trust score, applicable to the metadata attribute, using a defined probabilistic model, in response to the trust score being determined to satisfy a defined trust threshold, queuing a metadata update applicable to the metadata attribute, using a defined weighted priority process, determining a priority order for the metadata update among a group of metadata updates applicable to the group of zones of the multi-cloud architecture, and based on the priority order, initiating the metadata update.

Abstract: A system can execute tasks for a computer based on a prioritization of the tasks in a primary prioritization layer, according to a non-emergency task prioritization framework. The system can, based on identifying that an emergency criterion is satisfied with respect to the computer, performing priority reclassification of at least some tasks of the tasks, allocating first resources to an urgent task that is associated with the emergency criterion, wherein the urgent task has a higher priority than a highest priority of the tasks handled according to the non-emergency task prioritization framework, and allocating second resources to the highest priority task of the tasks concurrently with the allocating of the first resources to the urgent task. The system can, in response to the emergency criterion no longer being satisfied, revert to the non-emergency task prioritization framework.

Abstract: An information handling system includes a data vault that stores protected data and provides auxiliary data associated with the protected data. The system tags elements of the auxiliary data to elements of the protected data, marks each tagged element of the auxiliary data with a relevance level that indicates a relevance of the element of the auxiliary data to the protection of the associated element of protected data, sets a relevance level threshold, retains a first set of the tagged elements in a storage device, and discards a second set of the tagged elements. The first set of the tagged elements has relevance levels higher than the relevance level threshold, and the second set of the tagged elements has relevance levels lower than the relevance level threshold.

Abstract: An information handling system determines a sensitivity level for cloud resources, determines an encryption level for each of the cloud resources based on the sensitivity level, and encrypts data transfers between the information handling system and each of the cloud resources based on each cloud resource’s encryption level.

Abstract: The present disclosure relates to a system (300) for providing route guidance using augmented reality, the system includes a processor (502) to obtain a set of orientation parameters of a subject (304) based on one or more sensors accommodated in a computing device (302) associated with the subject and determine one or more motion parameters associated with the subject to reach the destination from a target location. The processor generates a set of arrows indicating at least one direction of the path from the target location of the subject to the destination, wherein when the set of orientation parameters deviates from the one or more motion parameters, the processor configured to calculate a degree of rotation to align the set of arrows indicating the at least one direction of the path along the desired direction to reach the destination to facilitate route guidance.

Abstract: An exemplary method of displaying an intraoperative image of a surgical site includes: receiving a plurality of images captured by a plurality of cameras, wherein the plurality of images capture the surgical site from a plurality of different perspectives; inputting an image of the plurality of images into a trained machine-learning model to determine if the image includes an obstruction to the surgical site; in accordance with a determination that the image includes the obstruction, generating, based on the plurality of images, a synthetic image that captures the surgical site from a synthetic perspective different from the plurality of different perspectives, wherein the synthetic image excludes the obstruction; and displaying the synthetic image as the intraoperative image of the surgical site.

Abstract: An information handling system is configured to receive a request for a trust ranking of a peripheral device being connected to another information handling system and validate a signature associated with the peripheral device. The information handling system is also configured to determine a trust ranking of the peripheral device when the validation of the signature is successful. In addition, the information handling system is configured to generate a response to the request and transmit the response to the other information handling system.

Abstract: An information handling system is configured to initiate a data transfer request from a first information handling system to a second information handling system and receive a response to the data transfer request from the second information handling system, wherein the response includes security configuration information. The information handling system is also configured to establish a secure data channel between the first information handling system and the second information handling system based on the security configuration information subsequent to the receipt of the response. In addition, the information handling system is configured to transfer data from the first information handling system to the second information handling system via the secure data channel.

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for extracting and tracing ridges at junctions, including confluences, corners, and terminals. For example, the disclosed systems generate, from a digital image, a pixel ridge using a distance transform and a depth-first traversal of pixels in the digital image. In some embodiments, the disclosed systems determine a junction within the pixel ridge by segmenting the pixel ridge into logical branches. In certain embodiments, the disclosed systems classify the junction as a confluence based on determining that the junction is made up of at least a threshold number of incident branches within the pixel ridge. In some embodiments, the disclosed systems reconstruct the confluence by detecting a region of deformity for the confluence and replacing pixels in the region of deformity with extrapolated pixels connecting incident branches.

Abstract: An information handling system includes a computer readable medium having an artificial intelligence (AI) application security model. The system further includes a processor operably coupled to the computer readable medium to access the AI application security model to gather business information for one or more applications, gather application vulnerability data, flag one or more at risk applications based on the vulnerability data, and assign a business vulnerability score for the one or more at risk application at least partially based on the business information for the one or more at risk application.

Abstract: A system controlling, in real time, user access to resources of an enterprise information technology (IT) infrastructure includes an activity detector configured to collect contextual data from data sources in response to a user attempting to access a resource of the enterprise IT infrastructure. A feature extraction engine coupled with the activity detector is configured to extract features from the contextual data collected by the activity detector. A behavior classifier coupled with the feature extraction engine is configured to implement a machine learning model that is trained to generate a role prediction by classifying behavior of the user based on input of the features. An access controller coupled with the behavior classifier is configured to assign a role priority to the user based on the prediction generated by the machine learning model, the role priority determining which resources of the enterprise IT infrastructure that the user is able to access.