Patent classifications
G06T2201/0063
Client forensic watermarking device, system, and method
A client forensic watermarking device, system, and method. A forensic watermarking device capable of communicating with a content server selecting a watermark mask area in which a watermark mask is displayed from video content and storing watermark area information about the watermark mask area in a storage unit according to the present disclosure may provide: a downloading unit requesting the video content to be played from the content server and receiving the video content and the watermark area information from the content server; a watermark mask generation unit outputting the watermark mask using the watermark area information inputted from the downloading unit; and an overlay unit superimposing the watermark mask inputted from the watermark mask generation unit on the watermark mask area of the video content inputted from the downloading unit, thereby enabling a client to display a forensic watermark so as to deal with a collusion attack.
DEVICE AND METHOD FOR INSERTING IDENTIFICATION CODE FOR TRACKING DUPLICATED IMAGE
The present disclosure a method of providing identification code insertion service for tracking a duplicated image, which is performed by a server, including: (a) receiving an image from a user terminal; (b) converting the received image to black and white, and selecting a plurality of insertion regions in the converted image; (c) transforming an image of at least one of a plurality of insertion regions selected at random; and (d) mapping an identification code and image information included in the transformed image of the insertion region, storing the identification code and the image information in a database, and providing the image in which the identification code is inserted to the user terminal.
Collusion attack prevention
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.
Difference attack protection
In one embodiment, a method for preventing a difference attack on watermarked video content is implemented on at least one computing device and includes: manipulating values of a set of pixels to embed a forensic watermark in at least one video frame in a video content item, where the manipulating is in accordance with a given magnitude of change in the values, and introducing random noise to the at least one video frame, where the random noise is random noise of the given magnitude.
COLLUSION ATTACK PREVENTION
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.
Watermarking method for high-definition map based on invisible characters
A watermarking method for a high-definition map based on invisible characters includes: firstly, establishing mapping relations between invisible characters and bit characters, a space character, and decimal digits; and combining watermark characters with corresponding positions thereof, adding Hamming code into a watermark character sequence, and converting the watermark character sequence into invisible characters to construct a composite watermark character sequence. Before watermark detection, a sequence of elements in map data is scrambled according to logistic chaotic mapping, and then the composite watermark character sequence is embedded according to the scrambled sequence. During watermark detection, the data are preprocessed, a sequence during watermark embedding is obtained, and then watermark information is extracted, errors are corrected, and an error correcting code is removed after correction to obtain final watermark information. According to the watermarking method, watermark embedding and watermark detection can be realized not changing data availability and high-accuracy characteristic.
Model anti-collusion watermark
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.
Collusion attack prevention
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.
DIFFERENCE ATTACK PROTECTION
In one embodiment, a method for preventing a difference attack on watermarked video content is implemented on at least one computing device and includes: manipulating values of a set of pixels to embed a forensic watermark in at least one video frame in a video content item, where the manipulating is in accordance with a given magnitude of change in the values, and introducing random noise to the at least one video frame, where the random noise is random noise of the given magnitude.
Watermark as honeypot for adversarial defense
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.