Thursdays the PTO publishes new pending patent applications. Both of today's Spotlight Applications concern aspects of digital fingerprinting. Assigned to Xecure Lab (TW), the first application discloses techniques for extracting digital fingerprints of a malicious document file. Assigned to Zeitera, the second patent discloses a media fingerprinting and identification system.
20130179975, "Method for Extracting Digital Fingerprints of a Malicious Document File," assigned to Xecure Lab Co., Ltd. (TW).
A method for extracting the genetic fingerprinting of a malicious document file includes the steps of establishing a database to store a plurality of genetic fingerprinting data of the first malicious document, then retrieving a document file sent via the Internet, and then proceeding with multi-point detection and extraction to the document file, so as to obtain a multi-point section, then comparing and analyzing the multi-point section with the plurality of genetic fingerprinting data of the first malicious document to confirm whether the multi-point section program code of the document file matches a malicious feature, thereby achieves the goal of extracting the content information of the document file and converts it into the genetic fingerprinting data of a new malicious document.
20130179452, "Media Fingerprinting and Identification System," assigned to Zeitera, LLC.
The overall architecture and details of a scalable video fingerprinting and identification system that is robust with respect to many classes of video distortions is described. In this system, a fingerprint for a piece of multimedia content is composed of a number of compact signatures, along with traversal hash signatures and associated metadata. Numerical descriptors are generated for features found in a multimedia clip, signatures are generated from these descriptors, and a reference signature database is constructed from these signatures. Query signatures are also generated for a query multimedia clip. These query signatures are searched against the reference database using a fast similarity search procedure, to produce a candidate list of matching signatures. This candidate list is further analyzed to find the most likely reference matches. Signature correlation is performed between the likely reference matches and the query clip to improve detection accuracy.