会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 1. 发明申请
    • METHODS AND APPARATUSES FOR USER-VERIFIABLE TRUSTED PATH IN THE PRESENCE OF MALWARE
    • 用于恶意软件存在的用户可验证路由的方法和设备
    • WO2011037665A2
    • 2011-03-31
    • PCT/US2010/040334
    • 2010-06-29
    • CARNEGIE MELLON UNIVERSITYMCCUNE, Jonathan, M.PERRIG, Adrian, M.DATTA, AnupamGILGOR, Virgil DorinQU, Ning
    • MCCUNE, Jonathan, M.PERRIG, Adrian, M.DATTA, AnupamGILGOR, Virgil DorinQU, Ning
    • G06F21/24
    • G06F21/57G06F21/85
    • An apparatus and method for establishing a trusted path (152) between a user interface (150) and a trusted executable (312), wherein the trusted path (152) includes a hypervisor (316) and a driver shim (314). The method includes measuring (710) an identity of the hypervisor; comparing (712) the measurement of the identity of the hypervisor with a policy for the hypervisor; measuring (714) an identity of the driver shim; comparing (716) the measurement of the identity of the driver shim with a policy for the driver shim; measuring (718) an identity of the user interface; comparing (720) the measurement of the identity of the user interface with a policy for the user interface; and providing (722) a human-perceptible indication of whether the identity of the hypervisor, the identity of the driver shim, and the identity of the user interface correspond with the policy for the hypervisor, the policy for the driver shim, and the policy for the user interface, respectively.
    • 一种用于在用户接口(150)和可信任可执行程序(312)之间建立可信路径(152)的装置和方法,其中所述可信路径(152)包括管理程序(316)和驱动器垫片(314)。 该方法包括测量(710)管理程序的身份; 比较(712)管理程序的身份的测量与管理程序的策略; 测量(714)驾驶员垫片的身份; 将(716)驾驶员垫片的身份测量与驾驶员垫片的策略进行比较; 测量(718)用户界面的身份; 将用户界面的身份的测量与用户界面的策略进行比较(720); 以及提供(722)关于管理程序的身份,驱动程序垫片的身份以及用户界面的身份是否符合管理程序的策略,驱动程序垫片的策略以及策略(722)的人为可察觉的指示 分别用于用户界面。
    • 2. 发明申请
    • SYSTEM AND METHOD FOR ASSISTING IN THE PROVISION OF ALGORITHMIC TRANSPARENCY
    • 用于协助提供算法透明度的系统和方法
    • WO2018081671A1
    • 2018-05-03
    • PCT/US2017/058943
    • 2017-10-30
    • CARNEGIE MELLON UNIVERSITY
    • DATTA, AnupamSEN, ShayakZICK, Yair
    • G06F19/24G06K9/62G06N7/06
    • The subject disclosure relates to devices, systems, and methods for algorithmic transparency into algorithmic decision-making systems. In non-limiting aspects, the disclosed subject matter facilitates generating a set of intervention inputs for an algorithmic decision-making system, observing the outcomes of the algorithmic decision-making system, and determining Quantitative Input Influence (QII) measures for the algorithmic decision-making system, wherein the at least one QII measure describes degree of influence of inputs on outcomes of the algorithmic decision-making system. In further non-limiting aspects, the disclosed subject matter facilitates generating transparency reports related to the QII measures, including transparency reports, regarding inputs, regarding individuals, and regarding groups of individuals, while maintaining privacy. Further non-limiting embodiments are provided that illustrate the advantages and flexibility of the disclosed subject matter.
    • 主题公开涉及用于算法决策制定系统的算法透明度的设备,系统和方法。 在非限制性方面,所公开的主题有利于为算法决策制定系统生成一组干预输入,观察算法决策制度的结果并且为算法决策制定系统确定定量输入影响(QII)度量, 其中至少一个QII度量描述输入对算法决策系统的结果的影响程度。 在进一步的非限制性方面中,所公开的主题便于生成与QII度量有关的透明度报告,包括关于投入,关于个人和关于个人群体的透明度报告,同时保持隐私。 提供了进一步的非限制性实施例,其说明了所公开主题的优点和灵活性。