Two models are first trained and then test images are applied to the two trained models in an effort to detect signature forgeries. The first model is trained with pairs of signature images and the resultant trained model is capable of detecting blind forgeries. The second model is trained with triplets of signature images and is capable of detecting skilled signature forgeries. After the two models are trained, test images are applied to the models and determinations are made as to whether a blind or skilled forgery is present.

Methods, systems, and apparatus, including a method for preventing fraud. In some aspects, a method includes: receiving, from multiple client devices, a measurement data element that includes a respective group member key and a group identifier for a given conversion as a result of displaying a digital component. Each client device uses a threshold encryption scheme to generate, based at least on network data that includes one or more of impression data or conversion data for the conversion, a group key that defines a secret for encrypting the network data and generate, based on data related to the application, the respective group member key that includes a respective share of the secret. In response to determining that at least the threshold number of measurement data elements having the same group identifier have been received, the network data is decrypted using the group member keys in the received measurement data elements.

A method for auditing an advertisement impression in which a first advertisement was presented in conjunction with first media content is disclosed. The method generally comprises transmitting to a plurality of second computing devices a plurality of randomly generated first cryptographic proofs; receiving, a first message from a second computing device indicating that the first advertisement was presented in conjunction with the first media content; and evaluating the first targeting model for the first advertisement based on the at least one media content classifier.

This disclosure relates to generating telecommunication network measurements. In one aspect, a method includes presenting, by a client device, a digital component that, when interacted with, initiates a call by the client device to a phone number specified by the digital component. A trusted program stores, in a presentation event data structure, a presentation event data element specifying the phone number and resource locator for a reporting system to which reports for the digital component are sent. The trusted program detects a phone call by the client device to a given phone number. The given phone number is compared to one or more presentation event data elements stored in the presentation event data structure. A determination is made that the given phone number matches the phone number specified by the digital component. In response, an event report is transmitted to the reporting system.

A computer-implemented method of generating a share of a digital signature of a message, wherein a threshold number of different signature shares from respective participants of a group of participants are required to generate the digital signature, wherein each participant has a respective private key share, the method being performed by a first one of the participants and comprising: generating a first message-independent component and a first message-dependent component, wherein the message-independent component is generated based on a first private key share and wherein the message-dependent component is generated based on the message; causing the first message-independent component to be made available to a coordinator; and causing a first signature share to be made available to the coordinator for generating the signature based on at least the threshold number of signature shares, wherein the first signature share comprises at least the message-dependent component.

Methods, systems, and computer-readable storage media for receiving an index and a random number from a verifier, receiving, from a shared data storage, encrypted supply chain data (SCD) of a supply chain actor (SCA), re-encrypting the encrypted SCD to provide re-encrypted SCD using a public encryption key of a decryption party, executing homomorphic operations on the re-encrypted SCD to provide an encrypted blinded result using second random numbers, receiving an encrypted modified blinded result, generating an encrypted blinded verification result using a verification function, the encrypted blinded result, the encrypted modified blinded result, and the random number, and sending the encrypted blinded verification result for decryption to provide a blinded verification result to the verifier, the verifier determining a verification result based on the blinded verification result and the random number, and comparing the verification result to a product claim.

Two models are first trained and then test images are applied to the two trained models in an effort to detect signature forgeries. The first model is trained with pairs of signature images and the resultant trained model is capable of detecting blind forgeries. The second model is trained with triplets of signature images and is capable of detecting skilled signature forgeries. After the two models are trained, test images are applied to the models and determinations are made as to whether a blind or skilled forgery is present.

Systems and methods that provide improved security and scalability in digital token exchange are disclosed. In one example, a system may receive from a requester one or more old cryptographically signed tokens each including a shared class and denomination. After validating the previously issued Value Tokens, the system may sign newly issued Value Tokens having the shared class and send them to the requester as a swap for the previously issued Value Tokens. Some tokens have intrinsic value while other coded Value Tokens require reference to a record of valid tokens to validate them. The system allows tokens of one type to be swapped for tokens of the other type, but issues intrinsic Value Tokens only as a swap for coded Value Tokens.

The invention provides a novel and unique system and method for cross channel in-vehicle identification of media, source, and consumption measurement and analysis. Real-time measurement and analysis of all applicable forms of media that a driver or passenger may consume inside of an automobile can be achieved. This includes AM/FM radio, Satellite Digital Audio Radio Service (SDARS), stored media such as CDs, MP3s & DVDs, streaming media, internet radio, audio books, podcasts, text-to-speech content, use of hands-free calling and other forms of audio, including content routed to the In Vehicle Entertainment (IVE) system through integration with a smartphone, media player or similar external Consumer Electronic (CE) device via wired or wireless connectivity, including but not limited to USB, Bluetooth, Wi-Fi, and the like, and also including integration platforms such as APPLE CARPLAY, GOOGLE ANDROID AUTO, HARMAN AHA RADIO, PANASONIC AUPEO, PIONEER ZYPR, FORD SYNC, MIRRORLINK, AIRBIQUITY CHOREO, and the like.

A computer-implemented method for escrowing secret data in a server of a client-server network, the client-server network comprising: a first client having at least one public and private client key pairs, at least one trusted client having at least one public and private trusted client key pairs, a server having a public and private server key pairs, a blockchain system comprising a plurality of nodes which are configured to store the public keys of the elements of the client-server network. It is also described a computer-implemented method for obtaining secret data of a server wherein the secret data is escrowed with the above computer-implemented method for escrowing secret data in a server. System, computer-readable mediums and computer programs, which are configured to implement or perform said computer-implemented methods, are also described.