Cisco Technology, Inc.

Cenek Skarda

Martin Kopp

Jan Kohout

Jan Brabec

Petr Somol

Danila Khikhlukha

Marc René Jacques Marie Dupont

Lukas Bajer

Tomas Komarek

Kyrylo Shcherbin

Jaroslav Hlavac

In one embodiment, a device obtains input features for a neural network-based model. The device pre-defines a set of neurons of the model to represent known behaviors associated with the input features. The device constrains weights for a plurality of outputs of the model. The device trains the neural network-based model using the constrained weights for the plurality of outputs of the model and by excluding the pre-defined set of neurons from updates during the training.

Learning of malicious behavior vocabulary and threat detection through behavior matching

Techniques for combining threat-related events associated with different modalities to provide a complete insight into cyber attack life cycles. The techniques may include receiving telemetry data associated with one or more modalities and detecting, based at least in part on the telemetry data, one or more abnormal events associated with security incidents. The one or more abnormal events may include at least a first abnormal event associated with a first modality and a second abnormal event associated with a second modality. The techniques may also include determining that an entity associated with the abnormal events is a same entity and, based at least in part on the entity comprising the same entity, determining that a correlation between the abnormal events is indicative of a security incident. Based at least in part on the correlation, an indication associated with the security incident may be output.

Comprehensible threat detection

Inverse imbalance subspace searching techniques are used to detect potential malware among samples of network communication data. A large number of samples of network communication data, such as proxy log data and/or network flows, are received and analyzed by a malware detection system. A number of the samples are associated with known malware, while other unlabeled samples are either benign or may be associated with unknown malware. An inverse imbalance subspace search may be performed, in which the sample sets are divided into subsets based on random feature thresholds, and each subset is evaluated based on the ratio of known malware samples to unlabeled samples. Unlabeled samples within subsets having high malware sample ratios may be identified, aggregated, and processed as potential malware.

Malware detection using inverse imbalance subspace searching

Growing community of inventors

Prague, Czechia

Cenek Skarda