Abstract: In some embodiments, a behavior classifier comprises a set of neural networks trained to determine whether a monitored software entity is malicious according to a sequence of computing events caused by the execution of the respective entity. When the behavior classifier indicates that the entity is malicious, some embodiments execute a memory classifier comprising another set of neural networks trained to determine whether the monitored entity is malicious according to a memory snapshot of the monitored entity. Applying the classifiers in sequence may substantially reduce the false positive detection rate, while reducing computational costs.

Abstract: In some embodiments, a behavioral computer security system protects clients and networks against threats such as malicious software and intrusion. A set of client profiles is constructed according to a training corpus of events occurring on clients, wherein each client profile represents a subset of protected machines, and each client profile is indicative of a normal or baseline pattern of using the machines assigned to the client respective profile. A client profile may group together machines having a similar event statistic. Following training, events detected on a client are selectively analyzed against a client profile associated with the respective client, to detect anomalous behavior. In some embodiments, individual events are analyzed in the context of other events, using a multi-dimensional event embedding space.

Abstract: In some embodiments, a behavior classifier comprises a set of neural networks trained to determine whether a monitored software entity is malicious according to a sequence of computing events caused by the execution of the respective entity. When the behavior classifier indicates that the entity is malicious, some embodiments execute a memory classifier comprising another set of neural networks trained to determine whether the monitored entity is malicious according to a memory snapshot of the monitored entity. Applying the classifiers in sequence may substantially reduce the false positive detection rate, while reducing computational costs.

Abstract: In some embodiments, a behavioral computer security system protects clients and networks against threats such as malicious software and intrusion. A set of client profiles is constructed according to a training corpus of events occurring on clients, wherein each client profile represents a subset of protected machines, and each client profile is indicative of a normal or baseline pattern of using the machines assigned to the client respective profile. A client profile may group together machines having a similar event statistic. Following training, events detected on a client are selectively analyzed against a client profile associated with the respective client, to detect anomalous behavior. In some embodiments, individual events are analyzed in the context of other events, using a multi-dimensional event embedding space.

Abstract: In some embodiments, a behavioral computer security system protects clients and networks against threats such as malicious software and intrusion. A set of client profiles is constructed according to a training corpus of events occurring on clients, wherein each client profile represents a subset of protected machines, and each client profile is indicative of a normal or baseline pattern of using the machines assigned to the client respective profile. A client profile may group together machines having a similar event statistic. Following training, events detected on a client are selectively analyzed against a client profile associated with the respective client, to detect anomalous behavior. In some embodiments, individual events are analyzed in the context of other events, using a multi-dimensional event embedding space.

Abstract: In some embodiments, a behavioral computer security system protects clients and networks against threats such as malicious software and intrusion. A set of client profiles is constructed according to a training corpus of events occurring on clients, wherein each client profile represents a subset of protected machines, and each client profile is indicative of a normal or baseline pattern of using the machines assigned to the client respective profile. A client profile may group together machines having a similar event statistic. Following training, events detected on a client are selectively analyzed against a client profile associated with the respective client, to detect anomalous behavior. In some embodiments, individual events are analyzed in the context of other events, using a multi-dimensional event embedding space.

Abstract: In some embodiments, a behavioral computer security system protects clients and networks against threats such as malicious software and intrusion. A set of client profiles is constructed according to a training corpus of events occurring on clients, wherein each client profile represents a subset of protected machines, and each client profile is indicative of a normal or baseline pattern of using the machines assigned to the client respective profile. A client profile may group together machines having a similar event statistic. Following training, events detected on a client are selectively analyzed against a client profile associated with the respective client, to detect anomalous behavior. In some embodiments, individual events are analyzed in the context of other events, using a multi-dimensional event embedding space.

Abstract: In some embodiments, a behavioral computer security system protects clients and networks against threats such as malicious software and intrusion. A set of client profiles is constructed according to a training corpus of events occurring on clients, wherein each client profile represents a subset of protected machines, and each client profile is indicative of a normal or baseline pattern of using the machines assigned to the client respective profile. A client profile may group together machines having a similar event statistic. Following training, events detected on a client are selectively analyzed against a client profile associated with the respective client, to detect anomalous behavior. In some embodiments, individual events are analyzed in the context of other events, using a multi-dimensional event embedding space.

Abstract: Described spam detection techniques including string identification, pre-filtering, and frequency spectrum and timestamp comparison steps facilitate accurate, computationally-efficient detection of rapidly-changing spam arriving in short-lasting waves. In some embodiments, a computer system extracts a target character string from an electronic communication such as a blog comment, transmits it to an anti-spam server, and receives an indicator of whether the respective electronic communication is spam or non-spam from the anti-spam server. The anti-spam server determines whether the electronic communication is spam or non-spam according to features of the frequency spectrum of the target string. Some embodiments also perform an unsupervised clustering of incoming target strings into clusters, wherein all members of a cluster have similar spectra.

Abstract: Described spam detection techniques including string identification, pre-filtering, and frequency spectrum and timestamp comparison steps facilitate accurate, computationally-efficient detection of rapidly-changing spam arriving in short-lasting waves. In some embodiments, a computer system extracts a target character string from an electronic communication such as a blog comment, transmits it to an anti-spam server, and receives an indicator of whether the respective electronic communication is spam or non-spam from the anti-spam server. The anti-spam server determines whether the electronic communication is spam or non-spam according to features of the frequency spectrum of the target string. Some embodiments also perform an unsupervised clustering of incoming target strings into clusters, wherein all members of a cluster have similar spectra.

Abstract: Described spam detection techniques including string identification, pre-filtering, and frequency spectrum and timestamp comparison steps facilitate accurate, computationally-efficient detection of rapidly-changing spam arriving in short-lasting waves. In some embodiments, a computer system extracts a target character string from an electronic communication such as a blog comment, transmits it to an anti-spam server, and receives an indicator of whether the respective electronic communication is spam or non-spam from the anti-spam server. The anti-spam server determines whether the electronic communication is spam or non-spam according to features of the frequency spectrum of the target string. Some embodiments also perform an unsupervised clustering of incoming target strings into clusters, wherein all members of a cluster have similar spectra.

Abstract: Described spam detection techniques including string identification, pre-filtering, and character histogram and timestamp comparison steps facilitate accurate, computationally-efficient detection of rapidly-changing spam arriving in short-lasting waves. In some embodiments, a computer system extracts a target character string from an electronic communication such as a blog comment, transmits it to an anti-spam server, and receives an indicator of whether the respective electronic communication is spam or non-spam from the anti-spam server. The anti-spam server determines whether the electronic communication is spam or non-spam according to certain features of the character histogram of the target string. Some embodiments also perform an unsupervised clustering of incoming target strings into clusters, wherein all members of a cluster have similar character histograms.

Abstract: Described spam detection techniques including string identification, pre-filtering, and frequency spectrum and timestamp comparison steps facilitate accurate, computationally-efficient detection of rapidly-changing spam arriving in short-lasting waves. In some embodiments, a computer system extracts a target character string from an electronic communication such as a blog comment, transmits it to an anti-spam server, and receives an indicator of whether the respective electronic communication is spam or non-spam from the anti-spam server. The anti-spam server determines whether the electronic communication is spam or non-spam according to features of the frequency spectrum of the target string. Some embodiments also perform an unsupervised clustering of incoming target strings into clusters, wherein all members of a cluster have similar spectra.

Abstract: Described spam detection techniques including string identification, pre-filtering, and character histogram and timestamp comparison steps facilitate accurate, computationally-efficient detection of rapidly-changing spam arriving in short-lasting waves. In some embodiments, a computer system extracts a target character string from an electronic communication such as a blog comment, transmits it to an anti-spam server, and receives an indicator of whether the respective electronic communication is spam or non-spam from the anti-spam server. The anti-spam server determines whether the electronic communication is spam or non-spam according to certain features of the character histogram of the target string. Some embodiments also perform an unsupervised clustering of incoming target strings into clusters, wherein all members of a cluster have similar character histograms.