Abstract: Document source detection uses unique copies to identify sources of leaked documents. The unique copies are generated from an original document and include a unique watermarking of one or more perturbations to a feature of the original document. An artifact, such as a photo or copy, is derived from one of the unique copies, the unique copy from which it was derived is identified. To identify the unique copy, unique copy keypoints in the unique copies are matched to artifact keypoints in the artifact to align the artifact with a location within the unique documents. Pixel regions in the unique copies that include perturbations are used to identify corresponding pixel regions in the artifact. Pixels in these regions are compared to identify the unique copy from which the artifact was derived, thus identifying a possible source of the leaked document.

Abstract: Information security is enhanced through watermarks that are unique for each recipient. Unique watermarking helps deter malicious information leaks because of the likelihood that the leaked information can be traced back to the source. To watermark images in a unique way for each recipient, candidate control points are determined for locations of image features within an image. The candidate control points that correspond to copy-resilient image features are identified. For generating each unique copy, a set of control points is selected from the candidate control points for the copy-resilient image features. An image is warped based on the selected set of control points. Since each set of control points is different, each warped image is distinct. The sets of control points can be saved and later used to recreate unique copies that are compared to recovered artifacts for source identification.

Abstract: For document source detection, text having a specific spacing pattern is rendered from unique versions of font files that identify an individual or device. If a document is leaked, and an artifact of it is recovered, the spacing pattern in the artifact can be used to determine the source of the document to identify the potential leak. To do so, unique string is generated for a user. The unique string is hashed, and font tables are modified to generate the unique font file version using the hash value. When text is generated using the unique font file version, glyph spacing is adjusted slightly according to the modified font table. A text classifier can be used to classify the relative spacing of glyphs in an artifact, and from values assigned by the classifier, a data sequence is determined. The data sequence is compared to hash values to identify the source.

Abstract: A document source is determined with high accuracy. Unique copies of an original document can be created. To determine which of the unique copies matches an artifact, keypoints of the unique copies and the artifact are identified. The unique copy keypoints are matched to the artifact keypoints. The unique copies are ranked based on the number of matching keypoints. An absolute match significance is determined from an absolute match fraction, comprising the number of matching unique copy keypoints for each unique copy relative to the total unique copy keypoints. A unique match significance is determined from a unique match fraction, comprising the number of uniquely matching keypoints for each unique copy relative to the total unique copy keypoints. The identification of the unique copy as matching the artifact is determined based on the absolute match significance and the unique match significance.

Abstract: Unique copies of an original document are generated by replacing spatial elements between bigrams with space characters of a uniform character code. An artifact is a derivation of a unique copy. To determine the unique copy from which the artifact was derived, bigrams of the artifact are determined. Spatial elements separating written units of the bigrams are determined to correspond with uniform character code characters, and their respective character identifiers are identified and associated with the bigrams. In some aspects, the spatial elements of the artifact are assigned binary spacing indicators that indicate their relative widths. In either or both events, a correlation can be determined between the character identifiers or the binary spacing indicators of the artifact and the character identifiers of the unique copies for respective bigrams. The unique copy having the strongest correlation is identified as being the unique copy from which the artifact was derived.

Abstract: Unique copies of an original document can be generated and provided to individual recipients. The unique copies can be used to identify the source of a document leak. The unique copies are generated by replacing terms within the original document with alternative terms. The alternative terms are determined using a first machine learning model that receives a term from the document and outputs the alternative terms. The output alternative terms are provided to a second machine learning model that indicates a tone for each alternative term. The tone of the alternative terms is compared to the tone of the term from the original document, and one or more of the alternative terms are selected based on the tone of the alternative terms relative to the tone of the document term. The alternative terms used to generate the unique copies have a same or similar tone as the document term.

Abstract: Document source detection uses unique copies to identify sources of leaked documents. The unique copies are generated from an original document and include a unique watermarking of one or more perturbations to a feature of the original document. An artifact, such as a photo or copy, is derived from one of the unique copies, the unique copy from which it was derived is identified. To identify the unique copy, unique copy keypoints in the unique copies are matched to artifact keypoints in the artifact to align the artifact with a location within the unique documents. Pixel regions in the unique copies that include perturbations are used to identify corresponding pixel regions in the artifact. Pixels in these regions are compared to identify the unique copy from which the artifact was derived, thus identifying a possible source of the leaked document.

Abstract: Unique copies of an original document can be generated and provided to individual recipients. The unique copies can be used to identify the source of a document leak. The unique copies are generated by replacing terms within the original document with alternative terms. The alternative terms are determined using a first machine learning model that receives a term from the document and outputs the alternative terms. The output alternative terms are provided to a second machine learning model that indicates a tone for each alternative term. The tone of the alternative terms is compared to the tone of the term from the original document, and one or more of the alternative terms are selected based on the tone of the alternative terms relative to the tone of the document term. The alternative terms used to generate the unique copies have a same or similar tone as the document term.

Abstract: An optical transceiver module which includes circuitry for detecting ambient light conditions in addition to circuitry for processing received optical data.

Abstract: A method of maintaining multiple routing tables within a global table of a network router including the steps of providing the router with a route table generator to maintain the global table, and a forwarding engine to perform table lookups, the performing of table lookups in one of the multiple routing tables of the global table using a key, the key representing an index into the one of said multiple routing tables within said global table, the key created by combining a virtual private network identification (VPN ID) and an address prefix, and maintaining a plurality of table entries in the global table by using the key as a pointer to one of said table entries.

Abstract: An optical transceiver module which includes circuitry for detecting ambient light conditions in addition to circuitry for processing received optical data.