Dell Products Inc.

Dell & Products L.p.

Emc IP Holding Company LLC

Ofir Ezrielev

Amihai Savir

Jehuda Shemer

Avitan Gefen

Nadav Azaria

Yehiel Zohar

Hanna Yehuda

Tomer Kushnir

Lee Serfaty

Kristen Jeanne Walsh

Maxim Balin

Boris Shpilyuck

Nicole Reineke

Inga Sogaard

Yevgeni Gehtman

Tomer Shachar

Igor Dubrovsky

Nisan Haimov

Oshry Ben Harush

Ilan Buyum

Ronen Rabani

Roman Bober

Eliyahu Rosenes

Yonit Lopatinski

Lior Gdaliahu

Amos Zamir

Naor Radami

Oshry Ben-Harush

Yonit Weiss

Maxim Grabov

Nomi Michaels

Or Herman Saffar

Hana Schuster Smith

Tsehsin Jason Liu

Noga Gershon

Pankaj Pande

Ganesh Ghodake

John Lawrence Dalton

Michael Thomas Krużewski

Yeh'iel Zohar

Oshry BenHarush

The technology described herein is directed towards mapping the storage tiers of various multi-cloud vendors to an enterprise's storage tiers and the enterprise's associated storage tier datasets, based on enterprise storage tiering definition data. Once mapped, the storage tier datasets are populated based on the vendor's per-tier metadata that are associated with the enterprise's data stored on that vendor's storage tiers. Similar mapping is performed for each other vendor's storage tiers. Once the storage tier datasets are populated based on the corresponding metadata, the metadata's variable parameters (e.g., performance metrics) for the enterprise's stored data can be presented according to the enterprise's own defined tiers and labels for the parameters. The metadata information in the datasets can be viewed per vendor and per enterprise-defined tier dataset, such as for object storage monitoring, cost comparison among different vendors' tiers, and closest vendor-to-enterprise parity comparisons of like variables.

Multi-cloud tiering translation to enterprise tiers

Redistributing disks based on disk wear patterns is disclosed. The wear patterns of disk drives in a storage system are learned or determined. When a restore operation is performed, the volumes to disk drive mappings are changed to balance the overall wear pattern of the storage system. This insures that, after the restore operation, disks that had comparatively lower wear levels are used more heavily while disks that had comparatively higher wear levels are used less heavily.

Redistribution of disks based on disk wear patterns

Methods and systems for managing an artificial intelligence (AI) model are disclosed. An AI model may be part of an evolving AI model pipeline, the processes of which may include obtaining training data from data sources used to update the AI model. An attacker may introduce poisoned training data via one or more of the data sources as a form of attack on the AI model. When the poisoned training data is identified, the poisoned training data may be compared to existing training data to determine the attacker's goal. Based on the attacker's goal, remedial actions may be performed that may update operation of pipeline. The updated operation of the pipeline may reduce the computational expense for remediating impact of the poisoned training data, and may reduce the likelihood of obtaining poisoned training data in the future.

Managing artificial intelligence models to identify goals of malicious attackers

Methods and systems for anomaly detection in a distributed environment are disclosed. To manage anomaly detection, a system may include an anomaly detector and one or more data collectors. The anomaly detector may detect anomalies in data obtained from one or more of the data collectors using an inference model. To perform anomaly detection, the inference model may require periodic re-training. Data collected from the one or more data collectors may be used to re-train the inference model as needed. Following anomaly detection and/or inference model re-training, the data may be discarded to remove the data from the anomaly detector.

System and method for memory-less anomaly detection

Methods and systems for managing data collection in a distributed system are disclosed. To manage data collection, the system may include a data aggregator and a data collector. The data aggregator and may utilize an inference model to predict data based on future measurements performed by data collectors throughout a distributed system without having access to the measurements. The data collectors may be mobile, and the data aggregator may direct the data collectors to various locations. To select paths for the data collectors to follow, the aggregator may utilize the level of uncertainty in predictions, the sensitivities in ranges of data to downstream consumers of the data collected by the data collectors, and/or other types of information. The data aggregator may select the paths for varying goals over time.

System and method for reduction of data transmission in dynamic systems

Methods and systems for managing operation of a deployment are disclosed. The deployment may be managed by employing redundant devices within the deployment. The redundant devices may serve to replace operation of failed devices. Despite replacement of operations of a failed device, the redundant device may not have similar functionality as the failed device. To make the functionality similar to the failed device, a correction factor may be applied to the redundant device. In applying the correction factor, the output from the redundant device may be expected to match output from the failed device. In matching output from the failed device, the redundant device may operate in place of the failed device.

Employing redundant devices in a deployment

Reinstating access to a system of an admin whose certificate is invalid or expired is disclosed. A requestor may send a request for reinstatement to tenant admins. The initiating tenant admin may initiate a voting operation to reinstate the requestor as an admin of a computing system. During the voting operation, multiple control points are implemented. At each control point, a key of the requestor is verified. The voting operation only proceeds when the key verification is successful. The voting operation is a gradual access recovery process where required keys are revealed over time and in a specific sequence.

Gradual access recovery in time and authorization

Methods and systems for identifying poisoned training data used for training artificial intelligence (AI) models are disclosed. To identify poisoned training data in a proposed training dataset, a causal model may be obtained. The causal model may include relationships relating data elements. The proposed training dataset may be identified as poisoned when data elements within the proposed training dataset do not satisfy the relationships set forth by the causal model. When the identification of poisoned training data is made, the AI model may not be updated using the proposed training dataset and the proposed training dataset may be discarded. If poisoned training data is not identified prior to training an AI model, methods and systems are disclosed for the remediation of the poisoned training dataset and subsequent tainted AI models. By doing so, the effect of poisoned training data may be prevented and/or efficiently computationally mitigated.

System and method for proactively identifying poisoned training data used to train artificial intelligence models

Methods and systems for prioritizing resources are disclosed. The resources in a deployment may be prioritized by training machine learning models for use in repairing impaired devices with failures of operation. The trained machine learning models may learn differences in operation. Differences in operation may pertain to output between each device of the set of devices and the digital twin in the deployment. The differences in operation may be used to prioritize a list of impaired devices that may be repaired. The prioritized list of impaired devices may be followed when available resources may be expended to repair the impaired devices.

Prioritizing resources for addressing impaired devices

Methods and systems for curating data by a data manager are disclosed. Data may be curated from various data sources before being provided to downstream consumers that may rely on the trustworthiness of the curated data in order to provide desired computer-implemented services. During the data curation process, data curation resources are used to improve the trustworthiness and/or value of the collected data. However, data curation resources (e.g., data curators, computing resources) may be limited and/or insufficient to perform the data curation process as desired, which may result in unusable and/or uncurated (e.g., untrustworthy) data. Thus, the data may be screened for anomalous data points. Features of the anomalous data points that meet importance criteria may be presented to the data source and the data source may indicate whether the features are expected. If the features are expected, the data pipeline may be populated with the anomalous data points.

Curating anomalous data for use in a data pipeline through interaction with a data source

Reinstating access to a system of an admin whose certificate is invalid or expired is disclosed using a secret that is remapped. When the admin's certificate is expired, the admin may send a request for reinstatement to tenant admins. The voting operation is based on shares of a secret that have been distributed to validators. When the shares are successfully reconstructed to obtain the secret, the voting operation is affirmed or allowed to proceed. The secret is remapped after a period of time. Remapping the secret includes creating a new secret and distributing new shares of the new secret to a different set of validators.

Improving decentralization of last resort recovery using secrets

Methods and systems for providing customized services to users of data processing systems are disclosed. To do so, a query may be obtained from a user. Contextual information for the query may be attempted to be obtained using a first data source associated with the user. If the portion of the contextual information is stored as a static data chunk in the first data source, the static data chunk may be obtained. If the portion of the contextual information is stored as a reference in the first data source, the reference may be obtained. The reference may indicate that the portion of the contextual information is available as a dynamic data chunk from another data source. The portion of the contextual information may be obtained using the static data chunk and/or the dynamic data chunk and the query may be serviced using at least the portion of the contextual information.

Managing contextual information for queries using data sources managed by personal agents

Methods and systems for managing sessions between guests and computer implemented services are disclosed. Upon initiating a session, it may be determined whether a guest wishes to remain anonymous during the session. If the guest wishes to remain anonymous and wishes for the anonymous session to be able to be continued, a session tracking token may be issued to the guest. Context information may be collected based on the guest's interactions with the computer implemented services and the context information may be associated with the session tracking token. If the guest wishes to continue the anonymous session at a future point in time, the guest may provide the context information and the session tracking token. If the context information and session tracking token are successfully validated, the previous anonymous session may be restored without linking the context information to an identity of the user.

Managing continuation of anonymous guest sessions

Methods and systems for managing operation of a deployment are disclosed. The operation of the deployment may be managed by simulating devices with a digital twin within the deployment. The digital twin may serve to replace operation of failed devices. By replacing failed devices with the digital twin, cooperative processes requiring participation of the failed devices may be continued while the failed devices are unable to participate.

Simulating devices with a digital twin in a deployment

Methods and systems for managing data collection are disclosed. To manage data collection, a system may include a data aggregator and data collectors. The data aggregator may utilize an inference model to predict the future operation of data collectors, and a pattern selection model to sample data from data collectors at a specific frequency and sequence. The pattern may specify that some data collectors are not to be sampled at various points in time. By doing so, the system may be able to transmit less data, consume less network bandwidth, and consume less energy throughout a distributed system while still providing access to aggregated data.

Growing community of inventors

Beer Sheva, Israel

Ofir Ezrielev