公开(公告)号：US12100193B2

公开(公告)日：2024-09-24

申请号：US17984824

申请日：2022-11-10

Applicant: PayPal, Inc.

Inventor： Jiyi Zhang

IPC: G06V10/44 ,  G06F18/214 ,  G06N3/045 ,  G06N3/08 ,  G06T1/00 ,  G06V10/764 ,  G06V10/82

CPC classification number: G06V10/454 ,  G06F18/214 ,  G06N3/045 ,  G06N3/08 ,  G06T1/005 ,  G06V10/764 ,  G06V10/82 ,  G06T2201/0063

Abstract: 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.

公开(公告)号：US09858633B2

公开(公告)日：2018-01-02

申请号：US15003690

申请日：2016-01-21

Applicant: Sony Corporation ,  Sony Pictures Entertainment Inc.

Inventor： Eric Diehl

IPC: G06K9/00 ,  G06T1/00 ,  H04L9/32

CPC classification number: G06T1/0021 ,  G06T1/005 ,  G06T2201/0063 ,  G09C5/00 ,  H04L9/32 ,  H04L2209/34 ,  H04L2209/606

Abstract: 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.

公开(公告)号：US20170270630A1

公开(公告)日：2017-09-21

申请号：US15505709

申请日：2015-08-20

Applicant: PHILIPS LIGHTING HOLDING B.V.

Inventor： MARTINUS PETRUS CREUSEN ,  RALPH KURT ,  FREDERIK JAN DE BRUIJN

IPC: G06T1/00 ,  G06F21/16 ,  G06F17/30 ,  H04N5/225 ,  H04N7/18

CPC classification number: G06T1/005 ,  G06F16/9535 ,  G06F21/16 ,  G06F2221/0737 ,  G06T2201/0063 ,  H04N5/2256 ,  H04N7/183

Abstract: A device comprises an image handling module for protecting an image of a scene captured by a camera. The image handling module is configured detect, in association with the image, a watermark signal having been embedded in light illuminating the scene at a respective geographic location. Further, the image handling module is configured to lookup the detected watermark signal in a privacy database, and based thereon to selectively inhibit use of the image.

公开(公告)号：US20170091611A1

公开(公告)日：2017-03-30

申请号：US15374729

申请日：2016-12-09

Applicant: SYS-TECH SOLUTIONS, INC.

Inventor： Michael L. Soborski

IPC: G06K19/10 ,  G06K19/08 ,  G06F17/30 ,  G06K19/06

CPC classification number: G06K19/10 ,  G06F17/30244 ,  G06F17/30247 ,  G06F17/3028 ,  G06F21/44 ,  G06F21/73 ,  G06K7/10 ,  G06K19/06028 ,  G06K19/06037 ,  G06K19/06112 ,  G06K19/086 ,  G06T1/0028 ,  G06T1/0042 ,  G06T2201/0063 ,  G06T2201/0201 ,  H04L9/3247 ,  H04L2209/56 ,  H04L2209/608 ,  H04L2209/805

Abstract: 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.

公开(公告)号：US09137415B2

公开(公告)日：2015-09-15

申请号：US14167618

申请日：2014-01-29

Applicant: Voir Inc.

Inventor： Stefano De Vuono ,  Kimberly Gordon

IPC: G06K9/00 ,  H04N1/32 ,  G06F21/10 ,  G06F21/16 ,  G06T1/00 ,  G06T11/60 ,  G06F11/30

CPC classification number: H04N1/32144 ,  G06F21/10 ,  G06F21/16 ,  G06F21/31 ,  G06F2221/0746 ,  G06F2221/0748 ,  G06T1/0021 ,  G06T1/0042 ,  G06T1/005 ,  G06T11/60 ,  G06T2201/0061 ,  G06T2201/0063 ,  G06T2201/0064 ,  H04N1/32272 ,  H04N2201/323 ,  H04N2201/3233 ,  H04N2201/3235 ,  H04N2201/3238 ,  H04N2201/327

Abstract: Among other things, at a cloud-based service, digital image files are received from which digital images can be displayed on devices. For each of the digital image files, data is embedded in the digital image file on behalf of a party who has rights in the digital image file. The existence of the embedded data is not perceptible in any digital image that is displayed using the digital image file. The embedded data includes information from which the digital image file can be authenticated. At the cloud-based service, a digital image file is received that is to be authenticated. The digital image file is authenticated based on the embedded data.

Abstract translation: 除了别的以外，在基于云的服务中，接收数字图像文件，数字图像可以从数字图像显示在设备上。 对于每个数字图像文件，代表在数字图像文件中具有权利的一方的数据嵌入在数字图像文件中。 在使用数字图像文件显示的任何数字图像中，嵌入数据的存在是不可察觉的。 嵌入的数据包括数字图像文件可从其认证的信息。 在基于云的服务中，接收到要认证的数字图像文件。 数字图像文件基于嵌入数据进行认证。

公开(公告)号：US20140226812A1

公开(公告)日：2014-08-14

申请号：US14258118

申请日：2014-04-22

Applicant: Scott A. Moskowitz

Inventor： Scott A. Moskowitz

IPC: H04L9/08

CPC classification number: H04L9/14 ,  G06T1/0028 ,  G06T1/005 ,  G06T1/0057 ,  G06T1/0064 ,  G06T2201/0051 ,  G06T2201/0052 ,  G06T2201/0053 ,  G06T2201/0061 ,  G06T2201/0063 ,  G06T2201/0065 ,  G06T2201/0083 ,  H04L9/0819 ,  H04L2209/04 ,  H04L2209/043 ,  H04L2209/046 ,  H04N1/3216 ,  H04N1/32187 ,  H04N1/32309 ,  H04N2201/3233 ,  H04N2201/324

Abstract: Multiple transform utilization and applications for secure digital watermarking In one embodiment of the present invention, digital blocks in digital information to be protected are transformed into the frequency domain using a fast Fourier transform. A plurality of frequencies and associated amplitudes are identified for each of the transformed digital blocks and a subset of the identified amplitudes is selected for each of the digital blocks using a primary mask from a key. Message information is selected from a message using a transformation table generated with a convolution mask. The chosen message information is encoded into each of the transformed digital blocks by altering the selected amplitudes based on the selected message information.

Abstract translation: 用于安全数字水印的多变换利用和应用在本发明的一个实施例中，要保护的数字信息中的数字块使用快速傅立叶变换被变换到频域。 为每个变换的数字块识别多个频率和相关联的幅度，并且使用来自密钥的主掩模为每个数字块选择所识别的幅度的子集。 从使用卷积掩码生成的变换表的消息中选择消息信息。 所选择的消息信息通过基于所选择的消息信息改变所选择的幅度而被编码到每个变换的数字块中。

公开(公告)号：US20110170737A1

公开(公告)日：2011-07-14

申请号：US12998143

申请日：2008-09-26

Applicant: Wan-yi Lin ,  Shan He ,  Jeffrey Adam Bloom

Inventor： Wan-yi Lin ,  Shan He ,  Jeffrey Adam Bloom

IPC: G06K9/00

CPC classification number: G06T1/005 ,  G06T2201/0051 ,  G06T2201/0063

Abstract: A method and apparatus are described including generating a unique code for each of a plurality of users using a plurality of symbols, generating a plurality of codes representing the plurality of symbols, substituting the plurality of codes into the unique code for each of the plurality of users, permuting the code resulting from the substitution to produce a codeword for each of the plurality of users and embedding the codeword into digital content. The second generating act further includes generating a string of first symbols followed by second symbols, wherein the first symbols are all ones and the second symbols are all negative ones, wherein a number of first symbols is equal to a number of the second symbols, and wherein if a length of the first symbols followed by the second symbols is less than a length of the code, then the first symbols followed by the second symbols are repeated until the code length is filled.

Abstract translation: 描述了一种方法和装置，包括使用多个符号为多个用户中的每一个生成唯一的代码，生成表示多个符号的多个代码，将多个代码替换为多个代码中的每一个的唯一代码 用户，将由替换产生的代码置换为多个用户中的每一个用户产生码字，并将码字嵌入数字内容。 第二生成动作还包括生成一串第一符号，后跟第二符号，其中第一符号全为1，第二符号全为负数，其中多个第一符号等于第二符号的数目，以及 其中如果所述第二符号之后的所述第一符号的长度小于所述代码的长度，则重复所述第二符号后面的所述第一符号直到所述代码长度被填充。

公开(公告)号：US20100146284A1

公开(公告)日：2010-06-10

申请号：US12521083

申请日：2008-01-13

Applicant: Zeev Geyzel ,  Leonid Dorrendorf

Inventor： Zeev Geyzel ,  Leonid Dorrendorf

IPC: G09G5/02 ,  H04N7/167

CPC classification number: G06T1/005 ,  G06T2201/0051 ,  G06T2201/0063 ,  G06T2201/0065 ,  G06T2201/0081

Abstract: A method and system for embedding data in video frames is described, the method comprising receiving marking information, representing the marking information as a 2-coordinate vector, denoted ω, where the 2-coordinates are denoted, respectively, α, β, such that ω=(α, β), providing a video frame to be marked, the video frame including a plurality of pixels, each pixel of the plurality of pixels being represented as p, where p=(x, y), x and y including coordinates of pixel p, the plurality of pixels being represented as a triad of color elements, denoted, respectively, as R, G, and B, and marking the video frame by transforming each pixel among the plurality of pixels as follows R′(p)=R(p)+R>, G′(p)=G(p)+G>, and B′(p)=B(p)+B>, where R> represents a dot product operation on p and ωR, G> represents a dot product operation on p and ωG, and B> represents a dot product operation on p and ωB.

Abstract translation: 描述了一种用于在视频帧中嵌入数据的方法和系统，所述方法包括接收表示标记信息的标记信息，所述标记信息表示为表示为ω的2坐标矢量，其中分别表示2坐标，α， 提供要被标记的视频帧，所述视频帧包括多个像素，所述多个像素中的每个像素表示为p，其中p =（x，y），x和 y包括像素p的坐标，多个像素被表示为色彩元素的三元组，分别表示为R，G和B，并且通过变换多个像素中的每个像素来标记视频帧如下R' （p）= R（p）+ R>，G'（p）= G（p）+ G>和B'（p）= B（p）+ B>，其中R> p和ωR，G>表示对p和ωG的点乘积运算，B>表示对p和ωB的点乘积运算。

公开(公告)号：US07624273B2

公开(公告)日：2009-11-24

申请号：US10752683

申请日：2004-01-08

Applicant: Hirofumi Muratani

Inventor： Hirofumi Muratani

IPC: H04L9/00

CPC classification number: G06T1/005 ,  G06T2201/0063 ,  G10L19/018 ,  H04H20/31 ,  H04H2201/50 ,  H04N1/32144 ,  H04N2201/3226 ,  H04N2201/3236 ,  H04N2201/324 ,  H04N2201/327

Abstract: Residue calculating sections respectively obtain residues which take a plurality of integers as modulus, with respect to a user ID. The plurality of integers are stored in modulus storage sections and are prime to each other. Based on these residues and parameters stored in a coding parameter storage section, component codes constructed by continuous sequences of 1 and 0 using a predetermined number of bits as a unit are respectively generated by component code generating sections. These component codes are concatenated by a concatenating section, thereby to obtain a code to be embedded, which constructs watermark information.

Abstract translation: 相对于用户ID，残差计算部分别分别获得以多个整数为模数的残差。 多个整数被存储在模数存储部分中并且彼此相互叠加。 基于存储在编码参数存储部中的这些残留和参数，分量代码生成部分分别生成以预定位数为单位的由1和0的连续序列构成的分量代码。 这些分量代码由级联部分连接，从而获得嵌入的代码，其构建水印信息。

公开(公告)号：US07397933B2

公开(公告)日：2008-07-08

申请号：US11139176

申请日：2005-05-27

Applicant: Mehmet Kivanc Mihcak ,  Yinian Mao

Inventor： Mehmet Kivanc Mihcak ,  Yinian Mao

IPC: G06K9/00

CPC classification number: H04N7/1675 ,  G06T1/005 ,  G06T2201/0063 ,  G09C5/00 ,  H04N5/765 ,  H04N5/913 ,  H04N21/2347 ,  H04N21/242 ,  H04N21/4405 ,  H04N21/835 ,  H04N21/8358 ,  H04N21/8547 ,  H04N2005/91307

Abstract: Systems and methods are described that desynchronize a video to be protected, thereby creating one or more digitally fingerprinted videos. In one implementation, a video to be protected is temporally desynchronized and spatially desynchronized. A fingerprinted copy of the video, as modified by the temporal and spatial desynchronizations, is created.

Abstract translation: 描述了系统和方法，使得要保护的视频失步，从而创建一个或多个数字指纹的视频。 在一个实现中，要保护的视频在时间上是不同步的并且在空间上是不同步的。 创建通过时间和空间去同步修改的视频的指纹副本。