Non-harmful data mimicking computer network attacks may be inserted in a computer network. Anomalous real network connections may be generated between a plurality of computing systems in the network. Data mimicking an attack may also be generated. The generated data may be transmitted between the plurality of computing systems using the real network connections and measured to determine whether an attack is detected.

Non-harmful data mimicking computer network attacks may be inserted in a computer network. Anomalous real network connections may be generated between a plurality of computing systems in the network. Data mimicking an attack may also be generated. The generated data may be transmitted between the plurality of computing systems using the real network connections and measured to determine whether an attack is detected.

Certain aspects of the present disclosure provide techniques for configuring data transmission. Aspects relate to determining a data transmission configuration utilizing a machine-learning based algorithm, such as a data transmission configuration for ultra-reliable low-latency communication (URLLC) applications. A method that may be performed by a base station (BS) includes receiving a feedback report from a user equipment (UE) including an indication of a first state corresponding to a plurality of channel condition parameters and determining one or more actions based, at least in part, on the first state. The BS may determining the one or more actions utilizing a machine learning algorithm that uses a second state, where the second state is based, at least in part, on the first state.

An example method for altering a transmission rate of a networking device. The example method comprises transmitting a first set of packets using first transmission characteristics represented by a first state of a finite state machine. The example method further comprises receiving information including a success status of transmission of the first set of packets. The example method also comprises updating, based on the received information, a weight of a first edge of the finite state machine, the first edge corresponding to a transition from a state representing prior transmission characteristics to the first state.

Low latency transmission time interval (TTI) structures and feedback configurations allow for a downlink transmission, a feedback indication indicating successful or unsuccessful reception of the downlink transmission, and a retransmission of the downlink transmission, within a same subframe or 1 ms time period. A TTI structure may include a number of shortened TTIs (sTTIs) that are transmitted in a subframe, and timing for feedback transmissions may be identified based at least in part on the TTI structure. The TTI structure and configurations for feedback timing may be dynamically or semi-statically determined by a user equipment (UE). In some cases, the TTI structure may include an identified partial sTTI allocated to a UE that may span fewer than all of the resources of a sTTI and allow for faster processing and generation of feedback information, and for faster retransmissions of unsuccessfully received transmissions.

A device may receive a first portion of network traffic associated with a flow. The device may perform a first upper layer inspection of the first portion of network traffic associated with the flow. The device may identify a set of parameters of the flow based on performing the first upper layer inspection of the first portion of network traffic associated with the flow. The device may determine, based on the set of parameters, a sampling rate at which to perform a second upper layer inspection of a second portion of network traffic associated with the flow. The device may instruct a lower layer to use the sampling rate to provide the second portion of network traffic associated with the flow for the second upper layer inspection. The device may perform the second upper layer inspection of the second portion of network traffic associated with the flow based on receiving the second portion of network traffic associated with the flow from the lower layer. The device may perform an action with regard to the flow based on a result of performing the second upper layer inspection.

In one embodiment, a system provides for optimizing an error rate of data through a communication channel. The system includes a data generator operable to generate a training sequence as a Markov code, and to propagate the training sequence through the communication channel. The system also includes a Soft Output Viterbi Algorithm (SOVA) detector operable to estimate data values of the training sequence after propagation through the communication channel. The system also includes an optimizer operable to compare the estimated data values to the generated training sequence, to determine an error rate based on the comparison, and to change the training sequence based on the Markov code to lower the error rate of the data through the communication channel.

Methods, systems, and devices for wireless communications are described that provide for a transmission of uplink control information (UCI) from a user equipment (UE) to a base station using uplink shared channel resources in the absence of other uplink shared channel data. Based in the UCI and uplink control parameters, the UE may determine an uplink power for transmission of the UCI based at least in part on a spectrum efficiency or a number of bits per resource element (BPRE) for the UCI.

A system, apparatus, computer-readable medium, and computer-implemented method are provided for detecting anomalous behavior in a network. Historical parameters of the network are determined in order to determine normal activity levels. A plurality of paths in the network are enumerated as part of a graph representing the network, where each computing system in the network may be a node in the graph and the sequence of connections between two computing systems may be a directed edge in the graph. A statistical model is applied to the plurality of paths in the graph on a sliding window basis to detect anomalous behavior. Data collected by a Unified Host Collection Agent (UHCA) may also be used to detect anomalous behavior.

Certain aspects of the present disclosure provide techniques for configuring data transmission. Aspects relate to determining a data transmission configuration utilizing a machine-learning based algorithm, such as a data transmission configuration for ultra-reliable low-latency communication (URLLC) applications. A method that may be performed by a base station (BS) includes receiving a feedback report from a user equipment (UE) including an indication of a first state corresponding to a plurality of channel condition parameters and determining one or more actions based, at least in part, on the first state. The BS may determining the one or more actions utilizing a machine learning algorithm that uses a second state, where the second state is based, at least in part, on the first state.