An inspection method is provided for checking the integrity of a combination of a security marking and an identification label, the security marking including at least one contrast field having a comparatively high reflectivity in a first and a second wavelength range, and a security field, having different reflection properties in the first wavelength range compared to the second wavelength range, and the identification label having at least one light background around mark components printed with dark color. The inspection method may include capturing possibly averaged gray values of the contrast field and the identification label background, comparing the gray values, and determining whether the gray value of the contrast field of the security marking deviates from the gray value of the background of the identification label by less than a predefined maximum amount.

Systems and methods for detection and localization of image and document forgery. The method can include the step of receiving a dataset having a plurality of authentic images and a plurality of manipulated images. The method can also include the step of benchmarking a plurality of image forgery algorithms using the dataset. The method can further include the step of generating a plurality of receiver operating characteristic (ROC) curves for each of the plurality of image forgery algorithms. The method also includes the step of calculating a plurality of area under curve metrics for each of the plurality of ROC curves. The method further includes the step of training a neural network for image forgery based on the plurality of area under curve metrics.

An information processing device comprises an electronic device, an averaging circuit acquiring output signals from the electronic device multiple times in a predetermined period and averaging the signals acquired multiple times, a memory circuit storing an averaged signal averaged by the averaging circuit and a PUF-ID extraction circuit generating a unique identifier based on the averaged signal.

A fraud confirmation assisting apparatus includes a light source, a reading sensor, and processing circuitry. The light source irradiates an object to be read with light in at least an invisible wavelength range. The reading sensor has sensitivity at least in the invisible wavelength range. The processing circuitry performs a reading operation on the object to be read by a combination of the light source and the reading sensor, and outputs a plurality of pieces of fraud confirmation information based on read information output from the reading sensor by the reading operation.

Systems and/or techniques for facilitating image forgery detection via pixel-metadata consistency analysis are provided. In various embodiments, a system can receive an electronic image from a client device. In various cases, the system can obtain a pixel vector and/or an image metadata vector that correspond to the electronic image. In various aspects, the system can determine whether the electronic image is authentic or forged, based on analyzing the pixel vector and the image metadata vector via at least one machine learning model.

A method is disclosed comprising: connecting, by a part scanner, to a blockchain platform; outputting a user interface, the user interface including at least a first input component and a second input component; capturing an image of a surface of a part; outputting the image in the user interface; generating a surface descriptor based on the image; when the first input component is activated, attempting to store, in the blockchain platform, an authentication record that is generated based on the surface descriptor, and outputting, in the user interface, an indication of an outcome of the attempt to store the authentication record in the blockchain platform; and when the second input component is activated, attempting to authenticate the part based on the surface descriptor and outputting, in the user interface, an indication of an outcome of the attempt to authenticate the part.

Systems, computer-implemented methods, and non-transitory machine-readable storage media are provided for detecting recapture attacks of images. One method comprises extracting one or more features from an image captured by a device; applying the one or more features as input to a trained machine learning model, wherein the trained machine learning model outputs a first score based on the extracted features; obtaining metadata of the image; performing a statistical analysis of the metadata of the image; generating a second score based on the statistical analysis of the metadata of the image; and generating a probability that the image is a recapture of an original image based on the first score and the second score.

A computer-implemented method for preventing unauthorized processing of a digital representation of at least a portion of a document, a device for data processing, and a computer program product are provided, wherein in particular the document is a banknote. The method comprises providing data, wherein the data is based on the digital representation of at least a portion of a test element. The digital representation may be an image file corresponding to the at least one portion of the test element. The method also involves analyzing the data with regard to data representing at least one characterizing feature of the at least one portion of the document. The method further comprises activating prohibiting means if the data being based on the digital representation of the at least one portion of the test element is similar to the data representing the at least one characterizing feature. The prohibiting means prohibit the data being based on the digital representation of the at least one portion of the test element to be further processed, in particular comprising copying and/or transmitting and/or printing and/or reproducing the data. Alternatively, the prohibiting means amend the data such that the data is prevented from being transmitted and/or printed and/or reproduced and/or further amended by data processing devices.

A method for identifying authenticity of an object, the method includes maintaining, in an identification server system, a reference image of an original object, the reference image and provided to represent all equivalent original objects, receiving, in the identification server system, one or more input images of the object to be identified, and generating, by the identification server system, a target image from the one or more input images. The method further includes aligning, by the identification server system, the target image with the reference image and analysing, by the identification server system, the target image in relation to the aligned reference image for identifying authenticity of the object.

The present disclosure generally relates to systems that include an artificial intelligence (AI) architecture for determining whether an image is manipulated. The architecture can include a constrained convolutional layer, separable convolutional layers, maximum-pooling layers, a global average-pooling layer, and a fully connected layer. In one specific example, the constrained convolutional layer can detect one or more image-manipulation fingerprints with respect to an image and can generate feature maps corresponding to the image. The global average-pooling layer can generate a vector of feature values by averaging the feature maps. The fully connected layer can then generate, based on the vector of feature values, an indication of whether the image was manipulated or not manipulated.