ALGORITHM CONSOLIDATION
    102.
    发明申请

    公开(公告)号:US20200272941A1

    公开(公告)日:2020-08-27

    申请号:US16754515

    申请日:2018-09-11

    IPC分类号: G06N20/00 G06N5/00

    摘要: This disclosure relates to a computer-implemented method of controlling an algorithm, and a device for implementing said method, the method including developing the algorithm from a first state to a second state by a machine learning process; determining a second computational cost of executing the algorithm in its second state; determining if the second computational cost satisfies a trigger condition; and, if so, consolidating the algorithm from the second state to a third state, wherein a third computational cost of executing the algorithm in its third state is less than the second computational cost.

    Signal identification
    103.
    发明授权

    公开(公告)号:US10754879B2

    公开(公告)日:2020-08-25

    申请号:US15739011

    申请日:2016-05-27

    摘要: A computer implemented method for identifying a signal in a sequence of numerical values, the method including: converting the sequence of numerical values into a vector sequence by converting each value in the sequence to a normalized vector representation; generating a vector field comprising the vector sequence as a multi-dimensional data structure such that vectors in the vector sequence are plotted in sequence in the vector field; modeling a simulated flow of particles through the vector field such that a flow of each particle is influenced by vectors in the vector field; generating one or more static representations of the particles, each representation being generated at a particular point in time; and performing feature detection on each of the one or more static representations to identify features in the representation corresponding to the signal.

    DISK ENCRYPTION
    104.
    发明申请
    DISK ENCRYPTION 审中-公开

    公开(公告)号:US20200257814A1

    公开(公告)日:2020-08-13

    申请号:US16073453

    申请日:2017-01-26

    IPC分类号: G06F21/62 G06F21/53 G06F9/455

    摘要: A computer implemented method of providing whole disk encryption for a virtualized computer system including providing a hypervisor having a data store and instantiating a disk image of the virtualized computer system as a first virtual machine (VM) having a virtual disk from which an operating system of the first VM can be booted; instantiating a second VM in the hypervisor including a software component executing therein, wherein the data store is a shared data store accessible by both the first and second VMs, the method further comprising: the software component accessing the first VM using privileged credentials to install a software agent in the first VM and to replicate the virtual disk of the first VM in the hypervisor data store as a duplicate disk, wherein the software agent is adapted to encrypt data written to, and decrypt data read from, the disk of the first VM at a runtime of the first VM; and the software component encrypting the duplicate disk and unmounting the copied disk and mounting the encrypted duplicate disk in the first VM so as to provide an encrypted disk for the first VM.

    Malware detection in migrated virtual machines

    公开(公告)号:US10733295B2

    公开(公告)日:2020-08-04

    申请号:US15541128

    申请日:2015-12-17

    IPC分类号: G06F21/56 G06F21/53 G06F9/455

    摘要: A malware detection system to detect malware in a virtual machine (VM), the system including a profile generator adapted to generate a profile of a deployment of the VM, the profile including execution characteristics of the deployment; a VM package generator to generate a VM package including: a VM descriptor describing a particular deployment of the VM; and an image of the particular deployment, the image including a representation of data stored for the particular deployment of the VM; and a malware identifier adapted to identify malware in a deployment of the VM responsive to the identification of a difference between profiles of multiple different deployments of the VM.

    Local and demand driven QoS models
    107.
    发明授权

    公开(公告)号:US10728157B2

    公开(公告)日:2020-07-28

    申请号:US15740852

    申请日:2016-06-30

    摘要: The present invention provides a method comprising: receiving a plurality of queries, each query specifying one or more quality-of-service (QoS) requirements for the transmission of a data flow in a network; determining a query prototype, the query prototype comprising at least one QoS component value based on the one or more QoS requirements; obtaining a plurality of items of route data, wherein each item of route data is associated with a corresponding route through the network and indicates a QoS component of the corresponding route; comparing the route data with the query prototype to identify routes which match the query prototype; and in the event that a selected number of routes match the query prototype, responding to a further query by transmitting a query response comprising a new QoS model based on the matching query prototype.

    MALICIOUS HOST DETECTION
    108.
    发明申请

    公开(公告)号:US20200228544A1

    公开(公告)日:2020-07-16

    申请号:US16636278

    申请日:2018-07-30

    IPC分类号: H04L29/06 G06N3/08 G06N3/04

    摘要: A method for detecting malware software in a computer system includes accessing a plurality of hostnames for a malware server from a computer system infected with malware and attempting to communicate with the malware server, each hostname including a plurality of symbols in each of a plurality of symbol positions; training an autoencoder based on each of the plurality of hostnames, wherein the autoencoder includes: a set of input units for each possible symbol and symbol position in a hostname; output units each for storing an output of the autoencoder; and a set of hidden units smaller in number than the set of input units and each interconnecting all input and all output units with weighted interconnections, such that the autoencoder is trainable to provide an approximated reconstruction of values of the input units at the output units; selecting a set of one or more symbol and symbol position tuples based on weights of interconnections in the trained autoencoder; and identifying infected computer systems based on their attempted communication to hostnames having symbols in symbol positions consistent with the tuples in the set.

    ANOMALY DETECTION IN COMPUTER NETWORKS
    109.
    发明申请

    公开(公告)号:US20200210782A1

    公开(公告)日:2020-07-02

    申请号:US16619745

    申请日:2018-06-08

    IPC分类号: G06K9/62 G06N3/04 H04L29/06

    摘要: A method of anomaly detection for network traffic communicated by devices via a computer network, the method including clustering a set of time series, each time series including a plurality of time windows of data corresponding to network communication characteristics for a device; training an autoencoder for each cluster based on time series in the cluster; generating a set of reconstruction errors for each autoencoder based on testing the autoencoder with data from time windows of at least a subset of the time series; generating a probabilistic model of reconstruction errors for each autoencoder; and generating an aggregation of the probabilistic models for, in use, detecting reconstruction errors for a time series of data corresponding to network communication characteristics for a device as anomalous.

    CELLULAR TELECOMMUNICATIONS NETWORK
    110.
    发明申请

    公开(公告)号:US20200100152A1

    公开(公告)日:2020-03-26

    申请号:US16574682

    申请日:2019-09-18

    摘要: A method in a cellular telecommunications network having a first central base station unit connecting to each of a plurality of distributed base station units, including identifying a cluster of distributed base station units within the plurality of distributed base station units, wherein each member of the cluster has a neighboring relationship with another member of the cluster that satisfies a threshold; using a first functional split in which a first set of protocol functions are implemented in the first central base station unit and a second set of protocol functions are implemented by each member of the cluster of distributed base station units; identifying a change in the membership of the cluster of distributed base station units; and, in response, causing the first central base station unit and each member of the cluster of distributed base station units to implement a second functional split in which a third set of protocol functions are implemented in the first central base station unit and a fourth set of protocol functions are implemented by each member of the cluster of distributed base station units.