-
公开(公告)号：US20240028947A1
公开(公告)日：2024-01-25
申请号：US17869095
申请日：2022-07-20
发明人： Giulio Zizzo , Ambrish Rawat , Naoise Holohan , Seshu Tirupathi
IPC分类号： G06N20/00
CPC分类号： G06N20/00
摘要： The present disclosure relates to a method comprising at training system iteratively training a machine learning algorithm using current training data. The current training data comprises a local dataset of a current task and a replay dataset and may be updated for a next iteration as follows. A training dataset may be received. If the training dataset is not s shared dataset and its task is different from the current task: information representing the local dataset may be shared with other training systems, the local dataset may be added to the replay dataset, and the received training dataset may be used as the local dataset for a next iteration. In case the task is the current task: the received training dataset may be added to the local dataset. If the training dataset is a shared dataset, the received training dataset may be added to the replay dataset.
-
公开(公告)号：US10997279B2
公开(公告)日：2021-05-04
申请号：US15859950
申请日：2018-01-02
摘要： Embodiments for watermarking anonymized datasets using decoys in a computing environment are provided. One or more decoy records may be embedded in an anonymized dataset such that a re-identification attack on the anonymized dataset targets the one or more decoy records.
-
公开(公告)号：US20200293675A1
公开(公告)日：2020-09-17
申请号：US16353540
申请日：2019-03-14
发明人： Spyridon Antonatos , Stefano Braghin , Naoise Holohan , Killian Levacher , Rahul Nair , Martin Stephenson
摘要： Systems, computer-implemented methods, and computer program products that can facilitate sensitive data policy recommendation are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise an extraction component that can employ an artificial intelligence model to extract compliance data from a data source. The computer executable components can further comprise a recommendation component that can recommend a sensitive data policy based on the compliance data. In some embodiments, the recommendation component can further identify one or more sensitive data entities of a sensitive data dataset that are affected by actionable obligation data of the data source.
-
4.发明申请公开(公告)号：US20190236305A1
公开(公告)日：2019-08-01
申请号：US15882583
申请日：2018-01-29
CPC分类号： G06F21/6245 , G06F16/951 , G06F21/10 , G06F2221/0737 , H04L43/04
摘要： Techniques facilitating automatically detecting unauthorized use of sensitive information in content communicated over a network are provided. A computer-implemented method can comprise receiving, by a system operatively coupled to a processor, from a first entity, data associated with the first entity and one or more rules defining use of the data by a second entity. The data and the one or more rules can be defined by the first entity. The computer-implemented method can also comprise analyzing, by the system, content communicated over a network by the second entity to determine whether the content violates the one or more rules. The computer-implemented method can further comprise generating, by the system, information indicative of one or more violations of the one or more rules based on a determination that the content violates the one or more rules.
-
公开(公告)号：US11200218B2
公开(公告)日：2021-12-14
申请号：US16386586
申请日：2019-04-17
摘要： Embodiments for performing consistent data masking in a distributed computing environment by a processor. A dictionary based data masking operation is performed on one or more datasets with causal ordering of the one or more datasets to enable reconstruction of a state of the one or more dictionaries for the one or more datasets.
-
公开(公告)号：US11132386B2
公开(公告)日：2021-09-28
申请号：US16276703
申请日：2019-02-15
IPC分类号： G06F16/28 , G06N5/02 , G06F16/2457
摘要： Various embodiments are provided for linking of anonymized datasets in a computing environment are provided. A number of linking records may be identified between an anonymized dataset and one or more non-anonymized datasets of a knowledge base according to one or more equivalence classes and a generalization level.
-
公开(公告)号：US10769306B2
公开(公告)日：2020-09-08
申请号：US15710917
申请日：2017-09-21
摘要： Embodiments for data anonymity by a processor. A dataset may be transformed into an anonymous dataset by applying a differential privacy operation and a clustering operation to the dataset.
-
公开(公告)号：US20200082290A1
公开(公告)日：2020-03-12
申请号：US16127694
申请日：2018-09-11
摘要： Techniques that facilitate adaptive anonymization of data using statistical inference are provided. In one example, a system includes an anonymization component and a statistical learning component. The anonymization component applies an anonymization strategy to data associated with an electronic device. The statistical learning component modifies the anonymization strategy to generate an updated anonymization strategy for the data based on a machine learning process associated with a probabilistic model that represents the data.
-
9.发明公开公开(公告)号：US20240249153A1
公开(公告)日：2024-07-25
申请号：US18166027
申请日：2023-02-08
发明人： Swanand Ravindra Kadhe , Heiko H. Ludwig , Nathalie Baracaldo Angel , Yi Zhou , Alan Jonathan King , Keith Coleman Houck , Ambrish Rawat , Mark Purcell , Naoise Holohan , Mikio Takeuchi , Ryo Kawahara , Nir Drucker , Hayim Shaul
摘要： Systems, devices, computer program products and/or computer-implemented methods of use provided herein relate to federated training and inferencing. A system can comprise a memory that stores computer executable components, and a processor that executes the computer executable components stored in the memory, wherein the computer executable components can comprise a modeling component that trains an inferential model using data from a plurality of parties and comprising horizontally partitioned data and vertically partitioned data, wherein the modeling component employs a random decision tree comprising the data to train the inferential model, and an inference component that responds to a query, employing the inferential model, by generating an inference, wherein first party private data, of the data, originating from a first passive party of the plurality of parties, is not directly shared with other passive parties of the plurality of parties to generate the inference.
-
公开(公告)号：US20240249018A1
公开(公告)日：2024-07-25
申请号：US18158299
申请日：2023-01-23
发明人： Ambrish Rawat , Naoise Holohan , Heiko H. Ludwig , Ehsan Degan , Nathalie Baracaldo Angel , Alan Jonathan King , Swanand Ravindra Kadhe , Yi Zhou , Keith Coleman Houck , Mark Purcell , Giulio Zizzo , Nir Drucker , Hayim Shaul , Eyal Kushnir , Lam Minh Nguyen
IPC分类号： G06F21/62
CPC分类号： G06F21/6245 , G06F21/6227
摘要： One or more systems, devices, computer program products and/or computer-implemented methods of use provided herein relate to a process for privacy-enhanced machine learning and inference. A system can comprise a memory that stores computer executable components, and a processor that executes the computer executable components stored in the memory, wherein the computer executable components can comprise a processing component that generates an access rule that modifies access to first data of a graph database, wherein the first data comprises first party information identified as private, a sampling component that executes a random walk for sampling a first graph of the graph database while employing the access rule, wherein the first graph comprises the first data, and an inference component that, based on the sampling, generates a prediction in response to a query, wherein the inference component avoids directly exposing the first party information in the prediction.
-
-
-
-
-
-
-
-
-
搜索结果
12 条记录 (耗时 0.022 秒)
