公开(公告)号：WO2013089758A1

公开(公告)日：2013-06-20

申请号：PCT/US2011/065284

申请日：2011-12-15

Applicant: INTEL CORPORATION ,  DURHAM, David M. ,  LONG, Men ,  GREWAL, Karanvir S. ,  DEWAN, Prashant ,  KANG, Xiaozhu

Inventor： DURHAM, David M. ,  LONG, Men ,  GREWAL, Karanvir S. ,  DEWAN, Prashant ,  KANG, Xiaozhu

IPC: G06F21/24 ,  G06F15/16

CPC classification number: H04L9/28 ,  G06F21/6263 ,  G06F2221/2107 ,  H04L9/065 ,  H04L63/0428 ,  H04N1/4486 ,  H04N21/2743 ,  H04N21/4405 ,  H04N21/4408 ,  H04N21/4788 ,  H04N21/8153

Abstract: An apparatus and method for preserving image privacy when manipulated by cloud services includes middleware for receiving an original image, splitting the original image into two sub-images, where the RGB pixel values of the sub-images have a bit value that is less than RGB pixel values of the original image. The sub-images are encrypted by adding a keystream to the RGB pixel values of the sub-images. The sub-image data is transmitted to a cloud service such as a social network or photo-sharing site, which manipulate the images by resizing, cropping, filtering, or the like. The sub-image data is received by the middleware and is successfully decrypted irrespective of the manipulations performed by the cloud services. In an alternative embodiment, the blocks of the original image are permutated when encrypted, and then reverse-permutated when decrypted.

Abstract translation: 一种用于在由云服务操作时保护图像隐私的装置和方法包括用于接收原始图像的中间件，将原始图像分割成两个子图像，其中子图像的RGB像素值具有小于RGB的比特值 原始图像的像素值。 通过向子图像的RGB像素值添加密钥流来加密子图像。 子图像数据被发送到诸如社交网络或照片共享站点的云服务，其通过调整大小，裁剪，过滤等来操纵图像。 子图像数据由中间件接收，并且被成功解密，而与云服务执行的操作无关。 在替代实施例中，原始图像的块在加密时被置换，然后在被解密时反向排列。

公开(公告)号：WO2013081596A1

公开(公告)日：2013-06-06

申请号：PCT/US2011/062585

申请日：2011-11-30

Applicant: INTEL CORPORATION ,  KANG, Xiaozhu ,  GEORGE, Biju ,  LUEH, Ken

Inventor： KANG, Xiaozhu ,  GEORGE, Biju ,  LUEH, Ken

IPC: G06F9/30 ,  G06F9/45

CPC classification number: G06F9/38 ,  G06F8/452 ,  G06F9/30 ,  G06F21/00

Abstract: Various embodiments are directed to a heterogeneous processor architecture comprised of a CPU and a GPU on the same processor die. The heterogeneous processor architecture may optimize source code in a GPU compiler using vector strip mining to reduce instructions of arbitrary vector lengths into GPU supported vector lengths and loop peeling. It may be first determined that the source code is eligible for optimization if more than one machine code instruction of compiled source code under-utilizes GPU instruction bandwidth limitations. The initial vector strip mining results may be discarded and the first iteration of the inner loop body may be peeled out of the loop. The type of operands in the source code may be lowered and the peeled out inner loop body of source code may be vector strip mined again to obtain optimized source code.

Abstract translation: 各种实施例涉及由同一处理器管芯上的CPU和GPU组成的异构处理器架构。 异构处理器架构可以使用向量带挖掘来优化GPU编译器中的源代码，以将任意矢量长度的指令减少到GPU支持的矢量长度和循环剥离。 如果编译源代码的多个机器码指令利用了GPU指令带宽限制，则可以首先确定源代码是否符合优化条件。 可以丢弃初始矢量条带挖掘结果，并且内环体的第一次迭代可能被剥离出环路。 可以降低源代码中的操作数类型，并且可以再次剥离源代码的剥离内圈体，以获得优化的源代码。

公开(公告)号：WO2013147908A1

公开(公告)日：2013-10-03

申请号：PCT/US2012/031753

申请日：2012-03-31

Applicant: INTEL CORPORATION ,  GREWAL, Karanvir S. ,  DURHAM, David M. ,  DEWAN, Prashant ,  KANG, Xiaozhu ,  LONG, Men

Inventor： GREWAL, Karanvir S. ,  DURHAM, David M. ,  DEWAN, Prashant ,  KANG, Xiaozhu ,  LONG, Men

IPC: H04N21/266

CPC classification number: H04N21/64715 ,  H04N21/23476 ,  H04N21/2541 ,  H04N21/266 ,  H04N21/4405 ,  H04N21/4627 ,  H04N21/8355

Abstract: Methods and systems for cryptographic access control of multimedia video, include embedding as metadata access control policy (ACP) information, including authorization rules and cryptographic information tied to an encryption policy, into encrypted video. An authorized receiver device having credentials and/or capabilities matched to the authorization rules is able to extract the ACP information from the encrypted video and use it to decrypt and properly render the video.

Abstract translation: 多媒体视频的密码访问控制方法和系统包括嵌入作为元数据访问控制策略（ACP）信息，包括与加密策略相关的授权规则和加密信息，加密视频。 具有与授权规则匹配的凭证和/或能力的授权的接收机设备能够从加密的视频中提取ACP信息，并使用它来解密并适当地呈现视频。

公开(公告)号：WO2015099670A1

公开(公告)日：2015-07-02

申请号：PCT/US2013/077565

申请日：2013-12-23

Applicant: INTEL CORPORATION ,  DEWAN, Prashant ,  SENGUPTA, Uttam ,  SAVAGAONKAR, Uday R. ,  CHHABRA, Siddhartha ,  DURHAM, David ,  KANG, Xiaozhu

Inventor： DEWAN, Prashant ,  SENGUPTA, Uttam ,  SAVAGAONKAR, Uday R. ,  CHHABRA, Siddhartha ,  DURHAM, David ,  KANG, Xiaozhu

IPC: G06T1/00 ,  G06T19/20

CPC classification number: G09C5/00

Abstract: Various embodiments are generally directed an apparatus and method for processing an encrypted graphic with a decryption key associated with a depth order policy including a depth position of a display scene, generating a graphic from the encrypted graphic when the encrypted graphic is successfully decrypted using the decryption key and assigning the graphic to a plane at the depth position of the display scene when the encrypted graphic is successfully decrypted.

Abstract translation: 各种实施例通常涉及一种用于使用与包括显示场景的深度位置的深度顺序策略相关联的解密密钥来处理加密图形的装置和方法，当使用解密成功解密加密图形时，从加密图形生成图形 并且当加密图形被成功解密时，将图形分配给显示场景的深度位置处的平面。

公开(公告)号：WO2013039476A1

公开(公告)日：2013-03-21

申请号：PCT/US2011/051261

申请日：2011-09-12

Applicant: INTEL CORPORATION ,  DEWAN, Prashant ,  DURHAM, David M. ,  KANG, Xiaozhu ,  GREWAL, Karanvir S.

Inventor： DEWAN, Prashant ,  DURHAM, David M. ,  KANG, Xiaozhu ,  GREWAL, Karanvir S.

IPC: H04L9/32 ,  H04N21/4415 ,  G06K9/78

CPC classification number: H04L9/3231 ,  G06F21/32 ,  G06F21/6209 ,  G06F2221/2109 ,  H04L9/0825 ,  H04L63/045 ,  H04L63/0861

Abstract: A method and device for securely sharing images across untrusted channels includes downloading an encrypted image from a remote server to a computing device. The encrypted image may be encrypted at the time of uploading by another user. The current user of the computing device is authenticated using a facial recognition procedure. If the current user is authenticated and is determined to be authorized to view the decrypted image, the encrypted image is decrypted and displayed to the user. If the user becomes unauthenticated (e.g., the user leaves the computing device or another user replaces the current user), the encrypted image is displayed in place of the encrypted image such that the decrypted image is displayed only for authorized persons physically present at the computing device.

Abstract translation: 一种用于在不信任信道上安全地共享图像的方法和设备包括将加密图像从远程服务器下载到计算设备。 加密图像可以在其他用户上传时被加密。 使用面部识别程序认证计算设备的当前用户。 如果当前用户被认证并被确定被授权以查看解密的图像，则加密的图像被解密并显示给用户。 如果用户变得未认证（例如，用户离开计算设备或另一用户替换当前用户），则加密图像被代替加密图像被显示，使得解密的图像仅针对被计算的物理存在的授权人员显示 设备。

公开(公告)号：WO2014022062A1

公开(公告)日：2014-02-06

申请号：PCT/US2013/049701

申请日：2013-07-09

Applicant: INTEL CORPORATION ,  DURHAM, David, M. ,  KANG, Xiaozhu ,  DEWAN, Prashant ,  LONG, Men ,  GREWAL, Karanvir, S.

Inventor： DURHAM, David, M. ,  KANG, Xiaozhu ,  DEWAN, Prashant ,  LONG, Men ,  GREWAL, Karanvir, S.

IPC: G06F21/60

CPC classification number: G06F21/10 ,  G06F21/32 ,  H04L9/0866 ,  H04L63/045 ,  H04L63/0861

Abstract: Embodiments of techniques and systems for biometric-data-based media encryption are described. In embodiments, an encryption key may be created for a recipient user based at least in part on biometric data of the recipient user. This encryption key may be maintained on a key maintenance component and used by a sharing user to encrypt a media file for access by the recipient user. One or more access policies associated with recipient user may be encrypted in the encrypted media file as well. In embodiments, the media file may be encrypted for use by multiple recipient users. When a recipient user desires to access the encrypted media file, a decryption key may be generated in real time based on contemporaneously captured biometric data and used to provide access to the encrypted media file. Other embodiments may be described and claimed.

Abstract translation: 描述了用于基于生物特征数据的媒体加密的技术和系统的实施例。 在实施例中，可以至少部分地基于接收者用户的生物特征数据为接收者用户创建加密密钥。 该加密密钥可以维护在密钥维护组件上，并由共享用户使用以加密媒体文件以供接收用户访问。 与接收者用户相关联的一个或多个访问策略也可以在加密的媒体文件中被加密。 在实施例中，媒体文件可以被加密以供多个接收者用户使用。 当接收者用户期望访问加密的媒体文件时，可以基于同时捕获的生物特征数据实时生成解密密钥，并且用于提供对加密的媒体文件的访问。 可以描述和要求保护其他实施例。

公开(公告)号：WO2013100898A1

公开(公告)日：2013-07-04

申请号：PCT/US2011/067367

申请日：2011-12-27

Applicant: INTEL CORPORATION ,  DEWAN, Prashant ,  DURHAM, David M. ,  HUANG, Ling ,  GREWAL, Karanvir S. ,  KANG, Xiaozhu

Inventor： DEWAN, Prashant ,  DURHAM, David M. ,  HUANG, Ling ,  GREWAL, Karanvir S. ,  KANG, Xiaozhu

IPC: G06K9/46

CPC classification number: G06F21/32 ,  G06K9/00288 ,  G06K9/00899

Abstract: A password-less method for authenticating a user includes capturing one or more images of a face of the user and comparing the one or more images with a previously collected face template. Randomly selected colored light and randomized blinking patterns are used to capture the images of the user. Such captured images are compared to previously collected face templates, thereby thwarting spoof attacks. A secret image, known only to the user and the device, is moved from one area of the display to another randomly selected area, using the movements of the user's head or face, thereby providing a Turing based challenge. Protected audio video path (PAVP) enabled devices and components are used to protect the challenge from malware attacks.

Abstract translation: 用于认证用户的无密码方法包括捕获用户的脸部的一个或多个图像并将一个或多个图像与先前收集的面部模板进行比较。 随机选择的彩色光和随机闪烁图案用于捕获用户的图像。 将这样的拍摄图像与先前收集的面部模板进行比较，从而阻止欺骗攻击。 使用用户和设备已知的秘密图像使用用户头部或脸部的移动从显示器的一个区域移动到另一个随机选择的区域，从而提供基于图灵的挑战。 受保护的音频视频路径（PAVP）启用的设备和组件用于保护挑战免受恶意软件攻击。