The present disclosure is generally directed to a method and computing device for determining whether a mark is genuine. According to various implementations, a computing device (or logic circuitry thereof) uses unintentionally-produced artifacts within a genuine mark to define an identifiable electronic signature, extracts certain attributes of the signature (such as deviation from the mean value for each band of the signature), and assigns numerical values to the extracted attributes in order to create a hash identifier that is significantly smaller than the electronic signature itself. The hash identifier is then used as an index for a database of electronic signatures (of genuine marks) to enhance the ease and speed with which numerous genuine signatures can be searched (e.g., in a database) and compared with signatures (of candidate marks.

A visual search system facilitates retrieval of provenance information using a machine learning model to generate content fingerprints that are invariant to benign transformations while being sensitive to manipulations. The machine learning model is trained on a training image dataset that includes original images, benign transformed variants of the original images, and manipulated variants of the original images. A loss function is used to train the machine learning model to minimize distances in an embedding space between benign transformed variants and their corresponding original images and increase distances between the manipulated variants and their corresponding original images.

Aspects of the disclosure relate to mitigation and detection of steganographic modifications embedded in images. A computing platform may receive an image embedded with steganographic modifications. The computing platform may change or modify any number of bits of one or more color components of one or more pixels of an image, rendering the steganographic modifications ineffective. The computing platform may cause at an isolation zone system, execution of an image, including steganographic modifications, to identify images embedded with steganographic modifications. The computing platform may also compare an image with image stored in an image storage module. The computing platform may store an image from the image storage module with a highest visual comparison score rather than the image.

An image forensics system estimates a camera response function (CRF) associated with a digital image, and compares the estimated CRF to a set of rules and compares the estimated CRF to a known CRF. The known CRF is associated with a make and a model of an image sensing device. The system applies a fusion analysis to results obtained from comparing the estimated CRF to a set of rules and from comparing the estimated CRF to the known CRF, and assesses the integrity of the digital image as a function of the fusion analysis.

A method of detecting tampering in a compressed digital image includes extracting one or more neighboring joint density features from a digital image under scrutiny and extracting one or more neighboring joint density features from an original digital image. The digital image under scrutiny and the original digital image are decompressed into a spatial domain. Tampering in the digital image under scrutiny is detected based on at least one difference in a neighboring joint density feature of the digital image under scrutiny and a neighboring joint density feature of the original image. In some embodiments, detecting tampering in the digital image under scrutiny includes detecting down-recompression of at least a portion of the digital image. In some embodiments, detecting tampering in the digital image includes detecting inpainting forgery in the same quantization.

Techniques for securing client watermarks are described herein. In accordance with various embodiments, a server receives a request from a client device for authorizing rendering a media content item at the client device. A validation engine on the server obtains at least a portion of an image representing a screen capture of rendering the media content item including a client watermark and/or metadata associated with the rendering. The validation engine then validates the watermark based at least in part on at least the portion of the image and/or the metadata. Having invalidated the client watermark, the server causes disruption of rendering the media content item at the client device. On the client side, a watermark engine captures the image of rendering the media content item including the client watermark and requests the server to validate the client watermark and renew the authorization based on the validation.

A method and a device for detecting copies or near-copies of images, comprises receiving an initial image, converting the initial image to grayscale, resizing the grayed image to a reduced image having a plurality of rows and an even number of columns, computing an overall signature for the reduced image, and determining whether the initial image is a copy or near-copy of an image according to the result of a comparison between the overall signature of the reduced image and reference image signatures. The step of computing the overall signature comprises the steps of computing a row signature for each row of the reduced image, the computation being based on a comparison of values obtained statistically across subsets of symmetrical pixels in each row, and concatenating the row signatures in order to obtain an overall signature.

The present disclosure is generally directed to a method and computing device for determining whether a mark is genuine. According to various implementations, a computing device (or logic circuitry thereof) uses unintentionally-produced artifacts within a genuine mark to define an identifiable electronic signature, extracts certain attributes of the signature (such as deviation from the mean value for each band of the signature), and assigns numerical values to the extracted attributes in order to create a hash identifier that is significantly smaller than the electronic signature itself. The hash identifier is then used as an index for a database of electronic signatures (of genuine marks) to enhance the ease and speed with which numerous genuine signatures can be searched (e.g., in a database) and compared with signatures (of candidate marks.

Methods and systems of detecting tampering in a digital image includes using hybrid large feature mining to identify one or more regions of an image in which tampering has occurred. Detecting tampering in a digital image with hybrid large feature mining may include spatial derivative large feature mining and transform-domain large feature mining. In some embodiments, known ensemble learning techniques are employed to address high feature dimensionality. detecting inpainting forgery includes mining features of a digital image under scrutiny based on a spatial derivative, mining one or more features of the digital image in a transform-domain; and detecting inpainting forgery in the digital image under scrutiny at least in part by the features mined based on the spatial derivative and at least in part by the features mined in the transform-domain.

Information processing with detection of the falsification of an image is disclosed. In one example, an information processing device includes a color conversion unit that makes an estimate of color conversion applied to a second image generated by image editing on a first image, and outputs a color conversion trial result in which color conversion according to the estimate is applied to the first image. A judgement unit compares the color conversion trial result with the second image to judge the presence or absence of falsification in the second image. The technology can be applied, for example, to a falsification detection system that detects whether image editing for falsifying an image has been performed when the image is uploaded to social media.