AN INTERACTIVE ARTIFICIAL INTELLIGENCE-BASED RESPONSE LOOP TO A CYBERATTACK

    公开(公告)号:WO2023091754A1

    公开(公告)日:2023-05-25

    申请号:PCT/US2022/050579

    申请日:2022-11-21

    Abstract: An intelligent orchestration component can facilitate an Al augmented and adaptive interactive response loop between multiple Al-based engines. A cyber threat detection uses Al to detect a cyber threat. An autonomous response engine uses Al to mitigate the detected cyber threat. A cyber-security restoration engine uses Al to remediate nodes in the system to a trusted operational state. The prediction engine uses Al to conduct simulations of cyberattacks to assist in determining how a simulated cyberattack might occur in the system, and how to use the simulated cyberattack information to preempt possible escalations of an ongoing actual cyberattack. The multiple Al-based engines bilaterally exchange behavioral metrics between the Al- based engines to work together to provide an overall cyber threat response during the ongoing cyberattack in light of continuing attack activities and simulations of the cyberattack to predict what might occur in the nodes based on the mitigation actions taken and/or the restoration actions taken.

    ARTIFICIAL INTELLIGENCE BASED ANALYST AS AN EVALUATOR

    公开(公告)号:WO2022150653A1

    公开(公告)日:2022-07-14

    申请号:PCT/US2022/011713

    申请日:2022-01-07

    Abstract: Methods, systems, and apparatus are disclosed for an Artificial Intelligence based cyber security system. An Artificial Intelligence based cyber analyst can make use of a data structure containing multiple tags to assist in creating a consistent, expanding modeling of an ongoing cyber incident. The Artificial Intelligence based cyber analyst can make use of a cyber incident graph database when rendering that incident to an end user. The Artificial Intelligence based cyber analyst can also be used as a mechanism to evaluate the quality of the alerts coming from 3rd parties' security tools both when the system being protected by the cyber security appliance is not actually under attack by a cyber threat as well as during an attack by a cyber threat.

    CERTIFICATE-BASED ENCRYPTION IMPLEMENTED WITH MULTIPLE ENCRYPTION SCHEMES

    公开(公告)号:WO2022125198A1

    公开(公告)日:2022-06-16

    申请号:PCT/US2021/055759

    申请日:2021-10-20

    Abstract: An encryption module and the decryption module cooperate with an identity-based key generator of users in a communication system in order to use an identity-based and certificate-based construction using two or more encryption schemes. An encrypted message is communicated between users of the communication system such that the encrypted message received by the device of the user needs keys from each of the two or more encryption schemes to be able to decrypt the encrypted message. The validation module cooperates with a limited-time of validity certificate issued from a certificate authority platform to decrypt the encrypted message via the limited-time of validity certificate. The validation module allows the decryption module to decrypt the encrypted message with the limited-time of validity certificate corresponding to an identity of the user when the user is determined to be actually validated for a period of time specified for the limited-time of validity certificate.

    USING A COMPLIANT LAYER TO ELIMINATE BUMP BONDING

    公开(公告)号:WO2020117334A1

    公开(公告)日:2020-06-11

    申请号:PCT/US2019/047760

    申请日:2019-08-22

    Abstract: Methods, systems, and apparatuses are described for a CMOS compatible substrate having multiple stacks of semiconductor layers. The multiple stacks, at least, each include i) a layer of a tellurium based semiconductor layer on top of ii) a porous silicon layer. The porous silicon layer is a compliant layer to accept structural defects from the tellurium based semiconductor layer into the porous silicon layer. The multiple stacks are grown on the CMOS compatible substrate.

    DEEP ADAPTIVE SEMANTIC LOGIC NETWORK
    9.
    发明申请

    公开(公告)号:WO2018208813A1

    公开(公告)日:2018-11-15

    申请号:PCT/US2018/031645

    申请日:2018-05-08

    Abstract: An artificial intelligence engine that has two or more modules cooperating with each other in order to create one or more machine learning models that use an adaptive semantic learning for knowledge representations and reasoning. The modules cause encoding the representations and reasoning from one or more sources in a particular field with terminology used by one or more human sources in that field into a set of rules that act as constraints and that are graphed into a neural network understandable by a first machine learning model, and then ii) adapting an interpretation of that set of encoded rules. The understanding of that set of encoded rules is adapted by i) allowing for semantically similar terms and ii) by conclusions derived from training data, to create an understanding of that set of encoded rules utilized by the machine learning model and the Al engine.

    FIRST STAGE PROCESS CONFIGURATIONS IN A 2-STAGE BIOREFORMING REACTOR SYSTEM

    公开(公告)号:WO2018200797A1

    公开(公告)日:2018-11-01

    申请号:PCT/US2018/029547

    申请日:2018-04-26

    Abstract: Disclosed herein is an integrated plant including, in some embodiments, an interconnected set of two or more stages of reactors forming a bio-reforming reactor configured to generate syngas from wood-containing biomass. A first stage of the bio- reforming reactor is configured to cause a set of chemical reactions in the biomass to produce reaction products of constituent gases, tars, chars, and other components. The first stage includes a fluidized-bed gasifier, a fluidized-bed combustor, and a moving-bed filtration system, each of which includes media inputs and outputs to respectively receive and supply heat-absorbing media to another operation unit for recirculation in a media recirculation loop. The moving-bed filtration system includes a tar pre-reformer configured to capture and reform heavier tars into lighter tars for subsequent processing in one or more fuel-producing reactor trains. Fuel products produced by the one or more reactor trains have a biogenic content of between 50% and 100%.

Patent Agency Ranking