Novel tools and techniques are provided for implementing monitoring and detection of fraudulent or unauthorized use in telephone conferencing systems or voice networks. In various embodiments, a computing system might monitor call activity through telephone conferencing system or voice network. In response to detecting use of the telephone conferencing system or voice network by at least one party based on the monitored call activity, the computing system might identify incoming and/or outgoing associated with a call initiated by the at least one party. The computing system might analyze the identified incoming and/or outgoing call data to determine whether the call initiated by the at least one party constitutes at least one of fraudulent use or unauthorized use of the telephone conferencing system or voice network. If so, the computing system might initiate one or more first actions.

An apparatus and method for determining a source of an unauthorized copy of speech signals in a conference call session. A conference bridge receives a speech signal during a conference call session with a plurality of end user devices attending. The conference bridge provides one or more dynamic, end user specific watermarks corresponding to the one or more end user devices. Each watermark is adjusted based on characteristics of the speech signal to make the watermark imperceptible to a human being. The speech signal is then embedded with the adjusted watermark in real time to generate a modified speech signal.

Embodiments described herein provide for performing a risk assessment using graph-derived features of a user interaction. A computer receives interaction information and infers information from the interaction based on information provided to the computer by a communication channel used in transmitting the interaction information. The computer may determine a claimed identity of the user associated with the user interaction. The computer may extract features from the inferred identity and claimed identity. The computer generates a graph representing the structural relationship between the communication channels and claimed identities associated with the inferred identity and claimed identity. The computer may extract additional features from the inferred identity and claimed identity using the graph. The computer may apply the features to a machine learning model to generate a risk score indicating the probability of a fraudulent interaction associated with the user interaction.

System and method for detecting SMS parameters manipulation. A first SMS registry is coupled to a first Short Message Service Center (SMSC) and optionally to other SMS registries. The first SMSC is within a terminating telephone network. The first SMS registry receives first and second information about an SMS message that was sent from another telephone network or from an External Short Messaging Entity (ESME) and is destined to the first SMSC. The first and second information represent status of the SMS message respectively before and after the SMS message enters the terminating telephone network. The first SMS registry or a firewall automatically compares at least corresponding portions of the first and second information. As a result of the comparison, in response to detecting a difference between the at least portions of the first and second information, the first SMS registry automatically sends a signal indicating SMS parameter manipulation.

A computer-implemented network verification system includes a second device situated in a terminating call network and configured to receive a call signal from a first device situated in an originating network. The first device is coupled to a first registry that stores originating call records. The first registry is configured to obtain, from the first device, and store call data and a SIP identity header associated with the call signal. The system also includes a second registry coupled to the second device and configured to receive, from the first registry over an out-of-band verification network, a first verification request that contains the originating call record, including the SIP identity header associated with the call signal. The second registry is further configured to send the SIP identity header contained in the first verification request to the second device.

A computer-implemented method for determining potentially undesirable voices, according to some embodiments, includes: receiving a plurality of audio recordings, the plurality of audio recordings comprising voices associated with undesirable activity, and determining a plurality of audio components of each of the plurality of audio recordings. The method may further comprise generating a multi-dimensional vector of audio components, from the plurality of audio components, for each of the plurality of audio recordings to generate a plurality of multi-dimensional vectors of audio components, and comparing audio components between the plurality of multi-dimensional vectors of audio components to determine a plurality of clusters of multi-dimensional vectors, each cluster of the plurality of clusters comprising two or more of the plurality of multi-dimensional vectors of audio components, wherein each cluster of the plurality of clusters corresponds to a blacklisted voice. The method may further comprise receiving an audio recording or audio stream, and determining whether the audio recording or audio stream is associated with a voice associated with undesirable activity based on a comparison to the plurality of clusters.

Techniques for caller verification in Rich Communication Services (RCS) for text messaging are discussed herein. A communication client can be the communication client designated to receive incoming communications for the user equipment. The user equipment may use the communication client to send, to a network device, a Session Initiation Protocol (SIP) instance to set communication client. The SIP instance may include a primary designator and a Universally Unique Identifier (UUID) associated with the client. The network device may store the information for the user equipment including the UUID and capability set. A second user equipment may poll the network device for the communications capabilities of the first user equipment before establishing a connection.

An example method of operation may include one or more of identifying an inbound call intended for a mobile device subscribed to a protected carrier network, determining the inbound call is assigned an origination telephone number that is subscribed to the protected carrier network, determining whether an inbound call origination source location indicates the protected carrier network or an out-of-network carrier network based on one or more call parameters received with the inbound call, and determining whether to transmit an indication to the mobile device that the inbound call has an elevated likelihood of being a scam call based on the inbound call origination source location.

A method and system for automatically blocking robocalls. A set of incoming call data is captured from the incoming call. The set of incoming call data, including captured audio data, is checked with plural different tests to determine if the robocall includes a voice call component. The plural different tests provide additional levels of detection for robocalls. The method and system automatically identify and process robocalls and help prevent call spoofing and neighbor spoofing by robocalls.

An information processing device (100) includes: a first acquisition unit (141) that acquires speech with which region information indicating a predetermined region and intention information indicating a caller intention are associated; and a generation unit (142) that generates a speech determination model for determining the intention information of speech constituting a processing object on the basis of the speech acquired by the first acquisition unit (141) and the region information associated with the speech.