Abstract: In one embodiment, a device in a network analyzes data regarding a detected anomaly in the network. The device determines whether the detected anomaly is a false positive. The device generates a white label for the detected anomaly based on a determination that the detected anomaly is a false positive. The device causes one or more alerts regarding the detected anomaly to be suppressed using the generated white label for the anomaly.

Abstract: In one embodiment, a device determines that a machine learning model is to be trained by a plurality of devices in a network. A set of training devices are identified from among the plurality of devices to train the model, with each of the training devices having a local set of training data. An instruction is then sent to each of the training devices that is configured to cause a training device to receive model parameters from a first training device in the set, use the parameters with at least a portion of the local set of training data to generate new model parameters, and forward the new model parameters to a second training device in the set. Model parameters from the training devices are also received that have been trained using a global set of training data that includes the local sets of training data on the training devices.

Abstract: In one embodiment, attack observations by a first node are provided to a user interface device regarding an attack detected by the node. Input from the user interface device is received that confirms that a particular attack observation by the first node indicates that the attack was detected correctly by the first node. Attack observations by one or more other nodes are provided to the user interface device. Input is received from the user interface device that confirms whether the attack observations by the first node and the attack observations by the one or more other nodes are both related to the attack. The one or more other nodes are identified as potential voters for the first node in a voting-based attack detection mechanism based on the attack observations from the first node and the one or more other nodes being related.

Abstract: In one embodiment, a device determines that input data to a machine learning model sent from a plurality of source nodes to an aggregation node is causing network congestion. A set of one or more other nodes to perform aggregation of the machine learning model input data is selected. A type of aggregation to be performed by the set of one or more other nodes is also selected. The set of one or more other nodes is also instructed to perform the selected type of aggregation on the data sent from the source nodes.

Abstract: In one embodiment, a first network device receives a notification that the first network device has been selected to validate a machine learning model for a second network device. The first network device receives model parameters for the machine learning model that were generated by the second network device using training data on the second network device. The model parameters are used with local data on the first network device to determine performance metrics for the model parameters. The performance metrics are then provided to the second network device.

Abstract: In one embodiment, attack traffic corresponding to a detected DoS attack from one or more attacker nodes is received at a denial of service (DoS) attack management node in a network. The DoS attack management node determines attack information relating to the attack traffic, including a type of the DoS attack and an intended target of the DoS attack. Then, the DoS attack management node triggers an attack mimicking action based on the attack information, where the attack mimicking action mimics a behavior of the intended target of the DoS attack that would be expected by the one or more attacker nodes if the DoS attack were successful.

Abstract: In one embodiment, a device in a network receives a set of output label dependencies for a set of attack detectors. The device identifies applied labels that were applied by the attack detectors to input data regarding a network, the applied labels being associated with probabilities. The device determines a combined probability for two or more of the applied labels based on the output label dependencies and the probabilities associated with the two or more labels. The device selects one of the applied labels as a finalized label for the input data based on the probabilities associated with the applied labels and on the combined probability for the two or more labels.

Abstract: In one embodiment, network data is received at a first node in a computer network. A low precision machine learning model is used on the network data to detect a network event. A notification is then sent to a second node in the computer network that the network event was detected, to cause the second node to use a high precision machine learning model to validate the detected network event.

Abstract: In one embodiment, local model parameters are generated by training a machine learning model at a device in a computer network using a local data set. One or more other devices in the network are identified that have trained machine learning models using remote data sets that are similar to the local data set. The local model parameters are provided to the one or more other devices to cause the one or more other devices to generate performance metrics using the provided model parameters. Performance metrics for model parameters are received from the one or more other devices and a global set of model parameters is selected for the device and the one or more other devices using the received performance metrics.

Abstract: In one embodiment, techniques are shown and described relating to a distributed approach for feature modeling on an LLN using principal component analysis. In one specific embodiment, a computer network has a plurality of nodes and a router. The router is configured to select one or more nodes of the plurality of nodes that will collaborate with the router for collectively computing a model of respective features for input to a Principal Component Analysis (PCA) model. In addition, the selected one or more nodes and the router are configured to perform a distributed computation of a PCA model between the router and the selected one or more nodes.

Abstract: In one embodiment, a device in a network detects a network attack using aggregated metrics for a set of traffic data. In response to detecting the network attack, the device causes the traffic data to be clustered into a set of traffic data clusters. The device causes one or more attack detectors to analyze the traffic data clusters. The device causes the traffic data clusters to be segregated into a set of one or more attack-related clusters and into a set of one or more clusters related to normal traffic based on an analysis of the clusters by the one or more attack detectors.

Abstract: In one embodiment, techniques are shown and described relating to attack mitigation using learning machines. A node may receive network traffic data for a computer network, and then predict a probability that one or more nodes are under attack based on the network traffic data. The node may then decide to mitigate a predicted attack by instructing nodes to forward network traffic on an alternative route without altering an existing routing topology of the computer network to reroute network communication around the one or more nodes under attack, and in response, the node may communicate an attack notification message to the one or more nodes under attack.

Abstract: In one embodiment, statistical information is collected relating to one or both of communication link quality or channel quality in a frequency-hopping network, in which packets are sent according to a frequency-hopping schedule that defines one or more timeslots, each timeslot corresponding to a transmission frequency. Also, a performance metric of a particular transmission frequency corresponding to a scheduled timeslot is predicted based on the collected statistical information. Based on the predicted performance metric, it is determined whether a transmitting node in the frequency-hopping network should transmit a packet during the scheduled timeslot using the particular transmission channel or wait until a subsequent timeslot to transmit the packet using another transmission frequency.

Abstract: For providing a simple monitoring mechanism with reduced resource and performance requirements a method for monitoring traffic in a network is claimed, wherein a monitoring activity of at least two monitoring probes of the network is coordinated by a coordinating element, wherein at least two nodes of the network are able to operate as coordinating elements and wherein the responsibility for coordinating the monitoring activity of the monitoring probes is split between the nodes according to a compressed representation of flow parameter keys. Further, an according network is described, preferably for carrying out the above mentioned method.

Abstract: A method for probabilistic processing of data, wherein the data is provided in form of a data set S composed of multidimensional n-tuples of the form (x1, . . . , xn), is characterized in that an n-dimensional data structure is generated by way of providing a bit matrix, providing a number K of independent hash functions Hk that are employed in order to address the bits in the matrix, and inserting the n-tuples (x1, . . . , xn) into the bit matrix by computing the hash values Hk(x) for all values x of the n-tuple for each of the number K of independent hash functions Hk, and by setting the resulting bits [Hk(x1), . . . , Hk(xn)] of the matrix. Furthermore, a respective system is disclosed.

Abstract: In one embodiment, a control loop control using a broadcast channel may be used to communicate with a node under attack. A management device may receive data indicating that one or more nodes in a computer network are under attack. The management device may then determine that one or more intermediate nodes are in proximity to the one or more nodes under attack, and communicate an attack-mitigation packet to the one or more nodes under attack by using the one or more intermediate nodes to relay the attack-mitigation packet to the one or more nodes under attack.

Abstract: In one embodiment, techniques are shown and described relating to quarantine-based mitigation of effects of a local DoS attack. A management device may receive data indicating that one or more nodes in a shared-media communication network are under attack by an attacking node. The management device may then communicate a quarantine request packet to the one or more nodes under attack, the quarantine request packet providing instructions to the one or more nodes under attack to alter their frequency hopping schedule without allowing the attacking node to learn of the altered frequency hopping schedule.

Abstract: In one embodiment, a device in a network identifies a set of traffic flow records that triggered an attack detector. The device selects a subset of the traffic flow records and calculates aggregated metrics for the subset. The device provides the aggregated metrics for the subset to the attack detector to generate an attack detection determination for the subset of traffic flow records. The device identifies one or more attack traffic flows from the set of traffic flow records based on the attack detection determination for the subset of traffic flow records.

Abstract: In one embodiment, a device in a network generates an expected traffic model based on a training set of data used to train a machine learning attack detector. The device provides the expected traffic model to one or more nodes in the network. The device receives an unexpected behavior notification from a particular node of the one or more nodes. The particular node generates the unexpected behavior notification based on a comparison between the expected traffic model and an observed traffic behavior by the node. The particular node also prevents the machine learning attack detector from analyzing the observed traffic behavior. The device updates the machine learning attack detector to account for the observed traffic behavior.

Abstract: In one embodiment, data flows are received in a network, and information relating to the received data flows is provided to a machine learning attack detector. Then, in response to receiving an attack detection indication from the machine teaming attack detector, a traffic segregation procedure is performed including: computing an anomaly score for each of the received data flows based on a degree of divergence from an expected traffic model, determining a subset of the received data flows that have an anomaly score that is lower than or equal to an anomaly threshold value, and providing information relating to the subset of the received data flows to the machine learning attack detector.