Abstract: Systems, methods, and computer-readable media for hierarchichal sharding of flows from sensors to collectors. A first collector can receive a first portion of a network flow from a first capturing agent and determine that a second portion of the network flow was not received from the first capturing agent. The first collector can then send the first portion of the network flow to a second collector. A third collector can receive the second portion of the network flow from a second capturing agent and determine that the third collector did not receive the first portion of the network flow. The third collector can then send the second portion of the network flow to the second collector. The second collector can then aggregate the first portion and second portion of the network flow to yield the entire portion of the network flow.

Abstract: An example method includes detecting, using sensors, packets throughout a datacenter. The sensors can then send packet logs to various collectors which can then identify and summarize data flows in the datacenter. The collectors can then send flow logs to an analytics module which can identify the status of the datacenter and detect an attack.

Abstract: Systems, methods, and computer-readable media for collector high availability. In some embodiments, a system receives, from a first collector device, a first data report generated by a capturing agent deployed on a host system in a network. The system can also receive, from a second collector device, a second data report generated by the capturing agent deployed on the host system. The first and second data reports can include traffic data captured at the host system by the capturing agent during a period of time. The system can determine that the first data report and the second data report are both associated with the capturing agent, and identify duplicate data contained in the first data report and the second data report. The system can then deduplicate the first and second data reports to yield a deduplicated data report.

Abstract: Systems, methods, and computer-readable media for annotating process and user information for network flows. In some embodiments, a capturing agent, executing on a first device in a network, can monitor a network flow associated with the first device. The first device can be, for example, a virtual machine, a hypervisor, a server, or a network device. Next, the capturing agent can generate a control flow based on the network flow. The control flow may include metadata that describes the network flow. The capturing agent can then determine which process executing on the first device is associated with the network flow and label the control flow with this information. Finally, the capturing agent can transmit the labeled control flow to a second device, such as a collector, in the network.

Abstract: An example method includes detecting, using sensors, packets throughout a datacenter. The sensors can then send packet logs to various collectors which can then identify and summarize data flows in the datacenter. The collectors can then send flow logs to an analytics module which can identify the status of the datacenter and detect an attack.

Abstract: Systems, methods, and computer-readable media for detecting sensor deployment characteristics in a network. In some embodiments, a system can run a capturing agent deployed on a virtualization environment of the system. The capturing agent can query the virtualization environment for one or more environment parameters, and receive a response from the virtualized environment including the one or more environment parameters. Based on the one or more environment parameters, the capturing agent can determine whether the virtualization environment where the capturing agent is deployed is a hypervisor or a virtual machine. The capturing agent can also determine what type of software switch is running in the virtualized environment.

Abstract: Systems, methods, and computer-readable media are provided for determining a packet's round trip time (RTT) in a network. A system can receive information of a packet sent by a component of the network and further determine an expected acknowledgement (ACK) sequence number associated with the packet based upon received information of the packet. The system can receive information of a subsequent packet received by the component and determine an ACK sequence number and a receiving time of the subsequent packet. In response to determining that the ACK sequence number of the subsequent TCP packet matches the expected ACK sequence number, the system can determine a round trip time (RTT) of the packet based upon the received information of the packet and the received information of the subsequent packet.

Abstract: Technologies for improving the accuracy of depth camera images include a computing device to generate a foreground mask and a background mask for an image generated by a depth camera. The computing device identifies areas of a depth image of a depth channel of the generated image having unknown depth values as one of interior depth holes or exterior depth holes based on the foreground and background masks. The computing device fills at least a portion of the interior depth holes of the depth image based on depth values of areas of the depth image within a threshold distance of the corresponding portion of the interior depth holes. Similarly, the computing device fills at least a portion of the exterior depth holes of the depth image based on depth values of areas of the depth image within the threshold distance of the corresponding portion of the exterior depth holes.

Abstract: A digital advertising system includes an advertisements module that provides a number of digital advertisements for display on a digital display device. A digital sign module including the digital display device displays digital advertisements provided by the advertisements module, and captures video analytics data relating to previous viewers of the digital advertisements displayed by the digital sign module. A data mining module retrieves the video analytics data from the digital sign module and generates trained advertising models based thereon using a data mining algorithm. A content management system module coupled to the advertisements module and the data mining module receives the digital advertisements and the trained advertising models and generates a subset of the advertisements thr display based on the trained advertising models.

Abstract: Systems, methods, and computer-readable media for identifying bogon addresses. A system can obtain an indication of address spaces in a network. The indication can be based on route advertisements transmitted by routers associated with the network. The system can receive a report generated by a capturing agent deployed on a host. The report can identify a flow captured by the capturing agent at the host. The system can identify a network address associated with the flow and, based on the indication of address spaces, the system can determine whether the network address is within the address spaces in the network. When the network address is not within the address spaces in the network, the system can determine that the network address is a bogon address. When the network address is within the address spaces in the network, the system can determine that the network address is not a bogon address.

Abstract: Systems, methods, and computer-readable media are provided for determining a packet's round trip time (RTT) in a network. A system can receive information of a packet sent by a component of the network and further determine an expected acknowledgement (ACK) sequence number associated with the packet based upon received information of the packet. The system can receive information of a subsequent packet received by the component and determine an ACK sequence number and a receiving time of the subsequent packet. In response to determining that the ACK sequence number of the subsequent TCP packet matches the expected ACK sequence number, the system can determine a round trip time (RTT) of the packet based upon the received information of the packet and the received information of the subsequent packet.

Abstract: Systems, methods, and computer-readable media for updating configurations in sensors deployed in multi-layer virtualized environments. In some examples, a system can track information of sensors and collectors in the network. In response to determining that a specific collector becomes unavailable (e.g., the specific collector is down, offline or becomes unsupported), the system can determine affected sensors corresponding to the specific collector, determine a new collector among active collectors of the network for each of the affected sensors, and dynamically update configuration and settings of the affected sensors to maintain proper collector-to-sensor mappings and other settings on the affected sensors.

Abstract: An example method includes detecting, using sensors, packets throughout a datacenter. The sensors can then send packet logs to various collectors which can then identify and summarize data flows in the datacenter. The collectors can then send flow logs to an analytics module which can identify the status of the datacenter and detect an attack.

Abstract: Systems, methods, and computer-readable media for detecting sensor deployment characteristics in a network. In some embodiments, a system can run a capturing agent deployed on a virtualization environment of the system. The capturing agent can query the virtualization environment for one or more environment parameters, and receive a response from the virtualized environment including the one or more environment parameters. Based on the one or more environment parameters, the capturing agent can determine whether the virtualization environment where the capturing agent is deployed is a hypervisor or a virtual machine. The capturing agent can also determine what type of software switch is running in the virtualized environment.

Abstract: Systems, methods, and computer-readable media for hierarchichal sharding of flows from sensors to collectors. A first collector can receive a first portion of a network flow from a first capturing agent and determine that a second portion of the network flow was not received from the first capturing agent. The first collector can then send the first portion of the network flow to a second collector. A third collector can receive the second portion of the network flow from a second capturing agent and determine that the third collector did not receive the first portion of the network flow. The third collector can then send the second portion of the network flow to the second collector. The second collector can then aggregate the first portion and second portion of the network flow to yield the entire portion of the network flow.

Abstract: Systems, methods, and non-transitory computer-readable storage media for synchronizing timestamps of a sensor report to the clock of a device. In one embodiment, the device receives a report from a sensor of a node. The report can include a network activity of the node captured by the sensor and a first timestamp relative to the clock of the node. The device can then determine a second timestamp relative to the clock of the collector indicating receipt of the report by the device and from the sensor at the node. The device can also determine a delta between the first timestamp and the second timestamp, and a communication latency associated with a communication channel between the device and the sensor. Next, the device can adjust the delta based on the communication latency, and generate a third timestamp based on the adjusted delta.

Abstract: Systems, methods, and computer-readable media for managing compromised sensors in multi-tiered virtualized environments. In some embodiments, a system can receive, from a first capturing agent deployed in a virtualization layer of a first device, data reports generated based on traffic captured by the first capturing agent. The system can also receive, from a second capturing agent deployed in a hardware layer of a second device, data reports generated based on traffic captured by the second capturing agent. Based on the data reports, the system can determine characteristics of the traffic captured by the first capturing agent and the second capturing agent. The system can then compare the characteristics to determine a multi-layer difference in traffic characteristics. Based on the multi-layer difference in traffic characteristics, the system can determine that the first capturing agent or the second capturing agent is in a faulty state.

Abstract: Managing a network environment to identify spoofed packets is disclosed. A method includes analyzing, via a first capture agent, packets processed by a first environment in a network associated with a first host, and analyzing, via a second capture agent, packets processed by a second environment in the network associated with a second host. The method includes collecting the first data and the second data at a collector and generating a topological map of the network and a history of network activity associated with the first environment and the second environment. The method includes extracting network data from a packet and comparing the extracted network data with stored network data in the database. When the comparison indicates that the extracted network data does not match the stored network data (i.e., the reported source does not match an expected source for the packet), determining that the packet is a spoofed packet.

Abstract: An example method includes calculating latency bounds for communications from two sensors to a collector (i.e., maximum and minimum latencies). After the collector receives an event report from the first sensor and an event report form the second sensor, the collector can determine, using the latency bounds, whether one event likely preceded the other.

Abstract: Systems, methods, and computer-readable media are provided for de-duplicating sensed data packets in a network. As data packets of a particular network flow move through the network, the data packets can be sensed and reported by various sensors across the network. An optimal sensor of the network can be determined based upon data packets reported by the various sensors. Data packets sensed and reported by the optimal sensor can be preserved for network analysis. Duplicative data packets of the particular network flow sensed and reported by other sensors of the network can be discarded to save storage capacity and processing power of network-flow analysis tools. Analysis of the particular network flow can be performed based upon the data packets sensed by the optimal sensor and non-duplicative data packets of the particular network-flow sensed by other sensors of the network.