A digital watermarking system and method are disclosed. In one respect, the disclosed digital watermarking includes generating an extracted signal by applying a watermark extractor to an original image, generating a mixed signal by mixing the first signal with a periodic watermark signal using a local weighting factor for the periodic watermark signal that attenuates a strength of the watermark signal in proportion to a pixel luminance level, and replacing the extracted signal in the original image with the mixed signal to generate a marked image, wherein the watermark signal is extractable from the marked image using the watermark extractor.

Embedding a watermark payload in content, including: a counter configured to store a random seed; a permutation generator configured to receive and process the watermark payload and the random seed, and generate a shuffled payload based on the random seed; and a watermark embedder configured to receive and embed the shuffled payload into the content. Key words include watermark payload and collusion.

Systems and methods are described for obfuscating variants of content segments. Variants of content segments can be used to encode an identifying sequence in a transmission of content. The variants of the content segments can each include one or more marked frames and one or more unmarked frames. Variations can be introduced into the unmarked frames for each of the variants of the content segments.

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.

First and second patterns are formed on a substrate. A spatial offset between the patterns is determined, and stored for later use in authenticating the substrate. (One or both of the patterns may convey steganographic information. One pattern may be printed, while the other may be embossed.) A smartphone can sense these patterns, determine the spatial offset, and check whether the determined offset matches the earlier-stored offset, to judge whether the substrate is authentic. Another arrangement effects serialization of product packaging by use of paired patterns (at least one of which is typically a watermark pattern) applied in a manner causing a spatial offset between the patterns to progressively vary along a length of a printed web. Still other arrangements involve substrates conveying patterns that degrade over time, e.g., indicating freshness or pressurization condition. A great variety of other features and arrangements are also detailed.

Embedding a watermark payload in content, including: a counter configured to store a random seed; a permutation generator configured to receive and process the watermark payload and the random seed, and generate a shuffled payload based on the random seed; and a watermark embedder configured to receive and embed the shuffled payload into the content. Key words include watermark payload and collusion.

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.

Systems, methods, and computer program products for determining an attack on a neural network. A data sample is received at a first classifier neural network and at a watermark classifier neural network, wherein the first classifier neural network is trained using a first dataset and a watermark dataset. The first classifier neural network determines a classification label for the data sample. A watermark classifier neural network determines a watermark classification label for the data sample. A data sample is determined as an adversarial data sample based on the classification label for the data sample and the watermark classification label for the data sample.