Patent application number | Description | Published |
20110067012 | SYSTEM AND METHOD FOR GENERATING WHITE-BOX IMPLEMENTATIONS OF SOFTWARE APPLICATIONS - A development suite for generating files, such as DRM-protected files, using white-box cryptography. The suite consists of a code generation tool, a data transformation engine, and a white-box data generation tool, and a white-box library. In the white-box cryptography context, the data transformation engine is used to protect the boundary between the cryptographic operation and the surrounding code. In particular, the data transformation engine is used to apply data transformations to the inputs to and outputs from the cryptographic operations. If the user specifies that transformations are required via a white-box parameterization file, the code generation tool puts the information specified by the user into a form the data transformation engine understands, namely as qualifiers on data variables and function prototypes. The data transformation engine then applies the specified transformations, and passes information to the data generation tool regarding which transformations were chosen. | 03-17-2011 |
20120192283 | Interlocked Binary Protection Using Whitebox Cryptography - A system and method for transforming a software application comprising binary code and optionally associated data, from an original form to a more secure form. The method includes performing a combination of binary transmutations to the application, and interlocking the transmutations by generating and placing interdependencies between the transmutations, wherein a transmutation is an irreversible change to the application. Different types of the transmutations are applied at varied granularities of the application. The transmutations are applied to the application code and the implanted code as well. The result is a transformed software application which is semantically equivalent to the original software application but is resistant to static and/or dynamic attacks. | 07-26-2012 |
20130024699 | System and Method for Protecting Cryptographic Assets From a White-Box Attack - A digital signature generation (DSG) process which provides resistance against white box attackers is disclosed. This is done by applying specially selected data transformations to the inputs, outputs and internal parameters of the algorithm. In particular, the signatory's private key does not appear in the clear in our protected implementation. Our new white box implementation produces signatures that are compatible with signatures created by conventional implementations; thus our solution facilitates interoperability and can be used as a drop-in replacement for conventional implementations. In particular, we describe transformations to the key (d) and the generator domain parameter (usually denoted G or g) of the digital signature generation processes, such that embodiments of the invention can produce signed messages which appear to a verifier as if the key (d) was used, without actually ever using the key (d). This makes it impossible for an adversary to ever observe the key (d), as it is not actually used. Further embodiments include additional protections to make it even harder for an adversary to deduce the key (d) by observing the process which generates the digital signature. | 01-24-2013 |
Patent application number | Description | Published |
20160063321 | SYSTEM AND METHOD FOR TRANSCRIBING HISTORICAL RECORDS INTO DIGITIZED TEXT - A handwriting recognition system converts word images on documents, such as document images of historical records, into computer searchable text. Word images (snippets) on the document are located, and have multiple word features identified. For each word image, a word feature vector is created representing multiple word features. Based on the similarity of word features (e.g., the distance between feature vectors), similar words are grouped together in clusters, and a centroid that has features most representative of words in the cluster is selected. A digitized text word is selected for each cluster based on review of a centroid in the cluster, and is assigned to all words in that cluster and is used as computer searchable text for those word images where they appear in documents. An analyst may review clusters to permit refinement of the parameters used for grouping words in clusters, including the adjustment of weights and other factors used for determining the distance between feature vectors. | 03-03-2016 |
20160063354 | SYSTEM AND METHOD FOR TRANSCRIBING HANDWRITTEN RECORDS USING WORD GROUPINGS BASED ON FEATURE VECTORS - A handwriting recognition system converts word images on documents, such as document images of historical records, into computer searchable text. Word images (snippets) on the document are located, and have multiple word features identified. For each word image, a word feature vector is created representing multiple word features. Based on the similarity of word features (e.g., the distance between feature vectors), similar words are grouped together in clusters, and a centroid that has features most representative of words in the cluster is selected. A digitized text word is selected for each cluster based on review of a centroid in the cluster, and is assigned to all words in that cluster and is used as computer searchable text for those word images where they appear in documents. An analyst may review clusters to permit refinement of the parameters used for grouping words in clusters, including the adjustment of weights and other factors used for determining the distance between feature vectors. | 03-03-2016 |
20160063355 | SYSTEM AND METHOD FOR TRANSCRIBING HANDWRITTEN RECORDS USING WORD GROUPING WITH ASSIGNED CENTROIDS - A handwriting recognition system converts word images on documents, such as document images of historical records, into computer searchable text. Word images (snippets) on the document are located, and have multiple word features identified. For each word image, a word feature vector is created representing multiple word features. Based on the similarity of word features (e.g., the distance between feature vectors), similar words are grouped together in clusters, and a centroid that has features most representative of words in the cluster is selected. A digitized text word is selected for each cluster based on review of a centroid in the cluster, and is assigned to all words in that cluster and is used as computer searchable text for those word images where they appear in documents. An analyst may review clusters to permit refinement of the parameters used for grouping words in clusters, including the adjustment of weights and other factors used for determining the distance between feature vectors. | 03-03-2016 |
Patent application number | Description | Published |
20090282014 | Systems and Methods for Predicting a Degree of Relevance Between Digital Ads and a Search Query - Systems and methods for predicting a degree of relevance between a set of candidate digital ads and a search query are disclosed. Generally, an ad provider receives a digital ad request associated with a search query. The ad provider identifies a set of candidate digital ads that may be served in response to the digital ad request. A relevance module extracts a set of features from the set of candidate digital ads and the search query associated with the digital ad request, and determines a degree of relevance between the set of candidate digital ads and the search query based on a prediction model and the extracted set of features. If the relevance module determines the set of candidate digital ads is relevant to the search query, the ad provider may serve one or more digital ads from the set of candidate digital ads in response to the received digital ad request. | 11-12-2009 |
20090282015 | Systems and Methods for Predicting a Degree of Relevance Between Digital Ads and Webpage Content - Systems and methods for predicting a degree of relevance between a set of candidate digital ads and webpage content are disclosed. Generally, an ad provider receives a digital ad request associated with webpage content. The ad provider identifies a set of candidate digital ads that may be served in response to the digital ad request. A relevance module extracts a set of features from the set of candidate digital ads and the webpage content, and determines a degree of relevance between the set of candidate digital ads and the webpage content based on a prediction model and the extracted set of features. If the relevance module determines the set of candidate digital ads is relevant to the webpage content, the ad provider may serve one or more digital ads from the set of candidate digital ads in response to the received digital ad request. | 11-12-2009 |
20090282016 | Systems and Methods for Building a Prediction Model to Predict a Degree of Relevance Between Digital Ads and a Search Query or Webpage Content - Systems and methods for building a prediction model to predict a degree of relevance between digital ads and a search query or webpage content are disclosed. Generally, an indication of relevance is received between a plurality of digital ads and one of a webpage content or a search query. A set of features is extracted from the plurality of digital ads and one of the webpage content or the search query. A prediction model is then built to predict a degree of relevance between the set of candidate digital ads and one of a second webpage content or a second search query, where the prediction model is built based at least one the received indication of relevance and the extracted set of features. | 11-12-2009 |
20100114933 | METHODS FOR IMPROVING THE DIVERSITY OF IMAGE SEARCH RESULTS - Techniques are described to increase the diversity or focus of image search results. A user submits an original query to search for images. A server generates a first results set by executing the original query using metadata associated with each image. The server selects, from the first results set, a specified number of results ranked highest and generates a list of terms from the metadata of each of the results selected. The terms may be only the tags of the results. The server generates an updated query using terms in the list that may be weighted based on the frequency of the term in the list or include only a specified number of the highest occurring terms in the list. The server generates a second results set by executing the updated query using metadata associated with each image. The second results set is then stored and displayed to the user. | 05-06-2010 |
20100121840 | QUERY DIFFICULTY ESTIMATION - In one embodiment, a method for estimating search query precision is provided, the method comprising: receiving a search query, wherein the search query contains one or more terms; retrieving documents from a collection based on the search query, wherein the retrieving includes only retrieving documents that contain all the terms of the search query; creating a query language model based on the retrieved documents; calculating a divergence between the query language model and the collection; and estimating search query precision based on the divergence, wherein the higher the divergence the more precise the search query. | 05-13-2010 |