COGNITIVE TESTING, DEBUGGING, AND REMEDIATION OF DRONE

    公开(公告)号:US20190272686A1

    公开(公告)日:2019-09-05

    申请号:US15909728

    申请日:2018-03-01

    Abstract: A computer-implemented method includes obtaining fault information regarding a fault associated with a first drone. The computer-implemented method additionally includes obtaining context parameter data of the first drone. The computer-implemented method additionally includes, responsive to obtaining the fault information and the context parameter data, determining to apply a first test case of a plurality of test cases based on a first risk value determined for the first test case using the context parameter data. The first test case is associated with the fault. The computer-implemented method additionally includes causing the first drone to initiate execution of the first test case.

    PUBLIC DEACTIVATION OF AUTONOMOUS VEHICLES
    13.
    发明申请

    公开(公告)号:US20190121355A1

    公开(公告)日:2019-04-25

    申请号:US15787756

    申请日:2017-10-19

    Abstract: Using an imaging device of a user device associated with a public user, an image of an autonomous vehicle (AV) operating in an area is captured. The public user associated with the user device is other than an occupant or controller of the AV. Image processing of the image is performed to extract a set of visual characteristics of the AV. A visual characteristic in the set of visual characteristics is insufficient to uniquely identify the AV. From a set of AVs a subset of candidate AVs is selected where each candidate AV in the subset of candidate AVs matches within a tolerance at least one visual characteristic in the set of visual characteristics, the subset of candidate AVs including the AV. A stop command is sent to the AV, causing the AV to execute a stopping operation resulting in a change in a velocity of the AV.

    Anonymization of traffic patterns over communication networks

    公开(公告)号:US10193776B2

    公开(公告)日:2019-01-29

    申请号:US15823799

    申请日:2017-11-28

    Abstract: A computer-implemented method of obfuscating communication traffic patterns may include detecting, at a first communications device, data communication sessions with a second communications device via the computer server using a network protocol. At the first device, a first traffic pattern is accessed based on the data communication sessions over a first predefined time period. At the first communications device, a second traffic pattern is accessed based on the data communication sessions over a second predefined time period that occurs after the first predefined time period. At the first communications device, based on a randomization process, a dummy data communication pattern is generated for transmission to the second communication devices, whereby the dummy data communication pattern is appended to the second traffic pattern for obfuscating a traffic pattern change between the first and the second traffic pattern at the computer server used to establish the communication sessions.

    Automatic Generation of Data-Centric Attack Graphs

    公开(公告)号:US20180330103A1

    公开(公告)日:2018-11-15

    申请号:US16041394

    申请日:2018-07-20

    CPC classification number: G06F21/577 G06F2221/034 H04L41/12 H04L63/1433

    Abstract: Generating an attack graph to protect sensitive data objects from attack is provided. The attack graph that includes nodes representing components in a set of components of a regulated service and edges between nodes representing relationships between related components in the set of components is generated based on vulnerability and risk metrics corresponding to each component. A risk score is calculated for each component represented by a node in the attack graph based on sensitivity rank and criticality rank corresponding to each respective component. Risk scores are aggregated for each component along each edge path connecting a node of a particular component to a node of a related component. In response to determining that an aggregated risk score of a component is greater than or equal to a risk threshold, an action is performed to mitigate a risk to sensitive data corresponding to the component posed by an attack.

    Selectively controlling a self-driving vehicle's access to a roadway

    公开(公告)号:US10109195B2

    公开(公告)日:2018-10-23

    申请号:US15800214

    申请日:2017-11-01

    Abstract: A processor-implemented method and/or computer program product selectively blocks a self-driving vehicle's access to a roadway. A vehicle interrogation hardware device receives an autonomous capability signal from an approaching self-driving vehicle. One or more processors compare the predefined roadway conditions to current roadway conditions of the access-controlled roadway. In response to the predefined roadway conditions matching the current roadway conditions of the access-controlled roadway within a predetermined range, the processor(s) determine whether the level of autonomous capability of the approaching self-driving vehicle is adequate to safely maneuver the approaching self-driving vehicle through the current roadway conditions of the access-controlled roadway. In response determining that the level of autonomous capability of the self-driving vehicle is not adequate to safely maneuver the approaching self-driving vehicle through the current roadway conditions of the access-controlled roadway, an automatic barricade controlling device positions an automatic barricade to block the approaching self-driving vehicle from accessing the access-controlled roadway.

Patent Agency Ranking