Abstract:
Methods and systems for obtaining reconstructing activities of target users in social networks, such as for decoding and displaying social network sessions held by a target user, or identifying other users who are associated with the target user. This analysis is typically carried out based on passive monitoring of network traffic. A social network decoding system constructs and maintains a replica database, which mimics a portion of the user profile database maintained by the social network servers. The social network decoding system monitors network traffic between users and social network servers. Based on the monitored traffic, the system gradually constructs a replica database that attempts to replicate a portion of the social network user profile database, relating to one or more predefined target users. Using the replica database, the system is able to correlate loosely-coupled information objects, events and interactions between the target users and social network pages.
Abstract:
Methods and systems to identify relationships between individuals by analyzing digital images and automatically detecting individuals who appear together in the images. A link analysis system accepts one or more digital images, and automatically recognizes individuals who appear together in the images. The system may recognize the individuals, for example, by applying a suitable face recognition process to the images. Upon identifying individuals who appear together, the system defines a relationship between them and acts upon the relationship.
Abstract:
A system and method in which one or more probing transactions are performed by transferring respective amounts of a cryptocurrency to one or more cryptocurrency addresses. The system then monitors and ascertains communications traffic exchanged with one or more IP addresses and that at least one of the probing transactions was downloaded to a particular IP address. The system then generates an output that can indicate an association between a cryptocurrency address of interest and the particular IP address.
Abstract:
Voice activity detection (VAD) is an enabling technology for a variety of speech based applications. Herein disclosed is a robust VAD algorithm that is also language independent. Rather than classifying short segments of the audio as either “speech” or “silence”, the VAD as disclosed herein employees a soft-decision mechanism. The VAD outputs a speech-presence probability, which is based on a variety of characteristics.
Abstract:
A method for expanding an initial ontology via processing of communication data, wherein the initial ontology is a structural representation of language elements comprising a set of entities, a set of terms, a set of term-entity associations, a set of entity-association rules, a set of abstract relations, and a set of relation instances. A method for extracting a set of significant phrases and a set of significant phrase co-occurrences from an input set of documents further includes utilizing the terms to identify relations within the training set of communication data, wherein a relation is a pair of terms that appear in proximity to one another.
Abstract:
Systems and methods of script identification in audio data obtained from audio data. The audio data is segmented into a plurality of utterances. A script model representative of a script text is obtained. The plurality of utterances are decoded with the script model. A determination is made if the script text occurred in the audio data.
Abstract:
A traffic-monitoring system that monitors encrypted traffic exchanged between IP addresses used by devices and a network, and further receives the user-action details that are passed over the network. By correlating between the times at which the encrypted traffic is exchanged and the times at which the user-action details are received, the system associates the user-action details with the IP addresses. In particular, for each action specified in the user-action details, the system identifies one or more IP addresses that may be the source of the action. Based on the IP addresses, the system may identify one or more users who may have performed the action. The system may correlate between the respective action-times of the encrypted actions and the respective approximate action-times of the indicated actions. The system may hypothesize that the indicated action may correspond to one of the encrypted actions having these action-times.
Abstract:
Systems and methods for obtaining authentication vectors issued, for use by a mobile communication terminal, by a Home Location Register (HLR) that serves a cellular communication network independently of any cooperation with the cellular network. Further to obtaining the authentication vectors, a terminal is caused to communicate over a WiFi WLAN using an encryption key derived from the obtained authentication vectors, e.g., per the EAP-SIM or EAP-AKA protocol. Since the encryption key is known, communication from the terminal is decrypted. The authentication vectors may be obtained by (i) an “impersonating” Visitor Location Register (VLR) server that does not serve the cellular network; (ii) an interrogation device which, by imitating a legitimate base station serving the cellular network, solicits the mobile communication terminal to associate with the interrogation device; or (iii) an SS7 probe, which obtains authentication vectors communicated from the HLR server to other entities on the SS7 network.
Abstract:
By formulizing a specific company's internal knowledge and terminology, the ontology programming accounts for linguistic meaning to surface relevant and important content for analysis. The ontology is built on the premise that meaningful terms are detected in the corpus and then classified according to specific semantic concepts, or entities. Once the main terms are defined, direct relations or linkages can be formed between these terms and their associated entities. Then, the relations are grouped into themes, which are groups or abstracts that contain synonymous relations. The disclosed ontology programming adapts to the language used in a specific domain, including linguistic patterns and properties, such as word order, relationships between terms, and syntactical variations. The ontology programming automatically trains itself to understand the domain or environment of the communication data by processing and analyzing a defined corpus of communication data.
Abstract:
Methods for obtain identifiers, such as International Mobile Subscriber Identities (IMSIs) and International Mobile Station Equipment Identities (IMEIs), of mobile communication terminals, and associate these identifiers with other items of identifying information provided by users of the terminals. A local interrogation device may be installed that imitates a legitimate base station belonging to a cellular network, at a control checkpoint. Local interrogation devices are connected to a global interrogation device in a hierarchical network, whereby the local interrogation devices are assigned a priority that is higher than that of the global interrogation device. The global interrogation device provides cellular coverage to a larger area that contains the control checkpoints, while the local interrogation devices provide more localized cellular coverage to the control checkpoints.