专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US11501001B2 Techniques to detect perturbation attacks with an actor-critic framework 有权
公开(公告)号：US11501001B2
公开(公告)日：2022-11-15
申请号：US16910722
申请日：2020-06-24
申请人： INTEL CORPORATION
发明人： Shih-Han Wang , Yonghong Huang , Micah Sheller , Cory Cornelius
IPC分类号： G06F21/57 , G06N5/04 , G06F21/56 , G06N20/00 , G06N3/08 , G06F21/55 , G06N3/00 , G06N3/04
摘要： Embodiments discussed herein may be generally directed to systems and techniques to generate a quality score based on an observation and an action caused by an actor agent during a testing phase. Embodiments also include determining a temporal difference between the quality score and a previous quality score based on a previous observation and a previous action, determining whether the temporal difference exceeds a threshold value, and generating an attack indication in response to determining the temporal difference exceeds the threshold value.

2. 发明申请

US20220012355A1 PROVISIONING FEDERATED COMPUTATION ON DISTRIBUTED PRIVATE DATA 有权
公开(公告)号：US20220012355A1
公开(公告)日：2022-01-13
申请号：US17483543
申请日：2021-09-23
申请人： Intel Corporation
发明人： Prakash Narayana Moorthy , Patrick Foley , Micah Sheller , Clair Bowman , G. Anthony Reina , Jason Martin , Shih-Han Wang
IPC分类号： G06F21/62 , G06F21/60
摘要： A method comprises receiving in a governor device, from a plurality of data owner devices, metadata for one or more datasets maintained by the plurality of data owner devices, registering the metadata for the one or more datasets with the governor device, in response to a request from an aggregator, providing at least a portion of the metadata for the one or more datasets to the aggregator, receiving, from the aggregator, a compute plan to be implemented by the plurality of data owner devices, distributing at least a portion of the compute plan to the plurality of data owner devices, in response to receiving, from the plurality of data owner devices, a verification report and a certification for an enclave, binding the enclave to a host device, and providing the compute plan to the plurality of data owner devices.

3. 发明申请

US20210374247A1 UTILIZING DATA PROVENANCE TO DEFEND AGAINST DATA POISONING ATTACKS 有权
公开(公告)号：US20210374247A1
公开(公告)日：2021-12-02
申请号：US17399019
申请日：2021-08-10
申请人： Intel Corporation
发明人： Salmin Sultana , Lawrence Booth, JR. , Mic Bowman , Jason Martin , Micah Sheller
IPC分类号： G06F21/57
摘要： The present invention discloses a secure ML pipeline to improve the robustness of ML models against poisoning attacks and utilizing data provenance as a tool. Two components are added to the ML pipeline, a data quality pre-processor, which filters out untrusted training data based on provenance derived features and an audit post-processor, which localizes the malicious source based on training dataset analysis using data provenance.

4. 发明授权

US09590966B2 Reducing authentication confidence over time based on user history 有权
标题翻译：根据用户历史，减少身份验证信心
公开(公告)号：US09590966B2
公开(公告)日：2017-03-07
申请号：US13840572
申请日：2013-03-15
申请人： Intel Corporation
发明人： Micah Sheller , Conor Cahill , Jason Martin , Brandon Baker
IPC分类号： G06F7/04 , H04L29/06 , G06F21/31 , G06F21/57
CPC分类号： H04L63/08 , G06F21/31 , G06F21/57 , G06F2221/2101 , G06F2221/2113 , G06F2221/2137 , G06F2221/2151
摘要： Technologies are provided in embodiments to manage an authentication confirmation score. Embodiments are configured to identify, in absolute session time, a beginning time and an ending time of an interval of an active user session on a client. Embodiments are also configured to determine a first value representing a first subset of a set of prior user sessions, where the prior user sessions of the first subset were active for at least as long as the beginning time. Embodiments can also determine a second value representing a second subset of the set of prior user sessions, where the prior user sessions of the second subset were active for at least as long as the ending time. Embodiments also determine, based on the first and second values, a decay rate for the authentication confidence score of the active user session. In some embodiments, the set is based on context attributes.
摘要翻译：在实施例中提供技术来管理认证确认分数。实施例被配置为在绝对会话时间中识别客户端上的活动用户会话的间隔的开始时间和结束时间。实施例还被配置为确定表示一组先前用户会话的第一子集的第一值，其中第一子集的先前用户会话活动至少等于开始时间。实施例还可以确定表示先前用户会话集合的第二子集的第二值，其中第二子集的先前用户会话活动至少等于结束时间。实施例还基于第一和第二值确定活动用户会话的认证置信度得分的衰减率。在一些实施例中，该集合基于上下文属性。

5. 发明申请

US20200327238A1 TECHNIQUES TO DETECT PERTURBATION ATTACKS WITH AN ACTOR-CRITIC FRAMEWORK 审中-公开
公开(公告)号：US20200327238A1
公开(公告)日：2020-10-15
申请号：US16910722
申请日：2020-06-24
申请人： INTEL CORPORATION
发明人： Shih-Han Wang , Yonghong Huang , Micah Sheller , Cory Cornelius
IPC分类号： G06F21/57 , G06N5/04 , G06F21/56 , G06N20/00 , G06N3/08 , G06F21/55 , G06N3/00 , G06N3/04
摘要： Embodiments discussed herein may be generally directed to systems and techniques to generate a quality score based on an observation and an action caused by an actor agent during a testing phase. Embodiments also include determining a temporal difference between the quality score and a previous quality score based on a previous observation and a previous action, determining whether the temporal difference exceeds a threshold value, and generating an attack indication in response to determining the temporal difference exceeds the threshold value.

6. 发明授权

US10726134B2 Techniques to detect perturbation attacks with an actor-critic framework 有权
公开(公告)号：US10726134B2
公开(公告)日：2020-07-28
申请号：US16103137
申请日：2018-08-14
申请人： INTEL CORPORATION
发明人： Shih-Han Wang , Yonghong Huang , Micah Sheller , Cory Cornelius
IPC分类号： G06F21/57 , G06N5/04 , G06F21/56 , G06N20/00 , G06N3/08 , G06F21/55 , G06N3/00 , G06N3/04
摘要： Embodiments discussed herein may be generally directed to systems and techniques to generate a quality score based on an observation and an action caused by an actor agent during a testing phase. Embodiments also include determining a temporal difference between the quality score and a previous quality score based on a previous observation and a previous action, determining whether the temporal difference exceeds a threshold value, and generating an attack indication in response to determining the temporal difference exceeds the threshold value.

7. 发明授权

US09450931B2 Reducing authentication confidence over time based on user history 有权
公开(公告)号：US09450931B2
公开(公告)日：2016-09-20
申请号：US13840572
申请日：2013-03-15
申请人： Intel Corporation
发明人： Micah Sheller , Conor Cahill , Jason Martin , Brandon Baker
IPC分类号： G06F7/04 , H04L29/06 , G06F21/31 , G06F21/57
摘要： Technologies are provided in embodiments to manage an authentication confirmation score. Embodiments are configured to identify, in absolute session time, a beginning time and an ending time of an interval of an active user session on a client. Embodiments are also configured to determine a first value representing a first subset of a set of prior user sessions, where the prior user sessions of the first subset were active for at least as long as the beginning time. Embodiments can also determine a second value representing a second subset of the set of prior user sessions, where the prior user sessions of the second subset were active for at least as long as the ending time. Embodiments also determine, based on the first and second values, a decay rate for the authentication confidence score of the active user session. In some embodiments, the set is based on context attributes.

8. 发明授权

US11556730B2 Methods and apparatus for distributed use of a machine learning model 有权
公开(公告)号：US11556730B2
公开(公告)日：2023-01-17
申请号：US15942131
申请日：2018-03-30
申请人： Intel Corporation
发明人： Micah Sheller , Cory Cornelius
IPC分类号： G06K9/62 , H04L67/10 , G06N20/00 , G06F16/951 , G06N3/063 , G06F21/62 , G06N3/04 , G06F21/74 , G06N3/08 , G06N99/00
摘要： Methods, apparatus, systems and articles of manufacture for distributed use of a machine learning model are disclosed. An example edge device includes a model partitioner to partition a machine learning model received from an aggregator into private layers and public layers. A public model data store is implemented outside of a trusted execution environment of the edge device. The model partitioner is to store the public layers in the public model data store. A private model data store is implemented within the trusted execution environment. The model partitioner is to store the private layers in the private model data store.

9. 发明申请

US20190042878A1 METHODS AND APPARATUS FOR DISTRIBUTED USE OF A MACHINE LEARNING MODEL 审中-公开
公开(公告)号：US20190042878A1
公开(公告)日：2019-02-07
申请号：US15942131
申请日：2018-03-30
申请人： Intel Corporation
发明人： Micah Sheller , Cory Cornelius
IPC分类号： G06K9/62 , G06N99/00 , H04L29/08 , G06F17/30
摘要： Methods, apparatus, systems and articles of manufacture for distributed use of a machine learning model are disclosed. An example edge device includes a model partitioner to partition a machine learning model received from an aggregator into private layers and public layers. A public model data store is implemented outside of a trusted execution environment of the edge device. The model partitioner is to store the public layers in the public model data store. A private model data store is implemented within the trusted execution environment. The model partitioner is to store the private layers in the private model data store.

10. 发明授权

US09762566B2 Reducing authentication confidence over time based on user history 有权
公开(公告)号：US09762566B2
公开(公告)日：2017-09-12
申请号：US15419447
申请日：2017-01-30
申请人： Intel Corporation
发明人： Micah Sheller , Conor Cahill , Jason Martin , Brandon Baker
IPC分类号： G06F7/04 , H04L29/06 , G06F15/16
CPC分类号： H04L63/08 , G06F21/31 , G06F21/57 , G06F2221/2101 , G06F2221/2113 , G06F2221/2137 , G06F2221/2151
摘要： Technologies are provided in embodiments to manage an authentication confirmation score. Embodiments are configured to identify, in absolute session time, a beginning time and an ending time of an interval of an active user session on a client. Embodiments are also configured to determine a first value representing a first subset of a set of prior user sessions, where the prior user sessions of the first subset were active for at least as long as the beginning time. Embodiments can also determine a second value representing a second subset of the set of prior user sessions, where the prior user sessions of the second subset were active for at least as long as the ending time. Embodiments also determine, based on the first and second values, a decay rate for the authentication confidence score of the active user session. In some embodiments, the set is based on context attributes.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式