Abstract: To perform pattern-based detection of malicious URLs, patterns are first generated from known URLs to build a pattern repository. A URL is first normalized and parsed, and keywords are extracted and stored in an additional repository of keywords. Tokens are then determined from the parsed URL and tags are associated with the parsed substrings. Substring text may also be replaced with general identifying information. Patterns generated from known malicious and benign URLs satisfying certain criteria are published to a pattern repository of which can be accessed during subsequent detection operations. During detection, upon identifying a request which indicates an unknown URL, the URL is parsed and tokenized to generate a pattern. The repository of malicious URL patterns is queried to determine if a matching malicious URL pattern can be identified. If a matching malicious URL pattern is identified, the URL is detected as malicious.

Abstract: The technology presented herein enables the use of a clustering algorithm to identify additional malicious domains based on known malicious domains. A domain identifier system identifies a first plurality of domain names associated with a malicious domain campaign and seeding a first clustering algorithm with the first plurality of domain names. After seeding the first clustering algorithm, the domain identifier system uses the first clustering algorithm to process passive domain name system (DNS) records to identify and group a second plurality of domain names associated with the malicious domain campaign.

Abstract: A system/process/computer program product for building multi-representational learning models for static analysis of source code includes receiving training data, wherein the training data includes a set of source code files for training a multi-representational learning (MRL) model for classifying malicious source code and benign source code based on a static analysis; generating a first feature vector based on a set of characters extracted from the set of source code files; generating a second feature vector based on a set of tokens extracted from the set of source code files; and performing an ensemble of the first feature vector and the second feature vector to form a target feature vector for classifying malicious source code and benign source code based on the static analysis.

Abstract: A process for magnetically sorting biological objects includes the steps of applying a magnetic field generated by a magnetic assembly to a flexible conduit; flowing a sample fluid containing magnetically labeled biological objects through the flexible conduit to collect the magnetically labeled biological objects on a conduit wall; removing the magnetic field from the flexible conduit; and mechanically deforming the flexible conduit to loosen the magnetically labeled biological objects collected on the conduit wall.

Abstract: Techniques for multi-representational learning models for static analysis of source code are disclosed. In some embodiments, a system/process/computer program product for multi-representational learning models for static analysis of source code includes receiving at a networked device a set comprising one or more multi-representation learning (MRL) models for static analysis of source code; performing a static analysis of source code associated with a sample received at the network device, wherein performing the static analysis includes using at least one MRL model; and determining that the sample is malicious based at least in part on the static analysis of the source code associated with the sample and without performing dynamic analysis of the sample, and in response to determining that the sample is malicious, performing an action based on a security policy.

Abstract: The present invention is directed to a method for sorting biological objects including the steps of providing a magnetic device that includes a conduit or channel having upstream and downstream sections and a magnetic means for generating first and second magnetic fields in the upstream and downstream sections, respectively; flowing a sample fluid that includes magnetically labeled biological objects and unlabeled biological objects through the upstream section to magnetically saturate the magnetically labeled biological objects by the first magnetic field; and flowing the sample fluid from the upstream section continuously to the downstream section to collect the magnetically labeled biological objects on a wall of the downstream section by the second magnetic field, wherein the first magnetic field in the upstream section has a higher average field strength than the second magnetic field in the downstream section.

Abstract: A system/process/computer program product for building multi-representational learning models for static analysis of source code includes receiving training data, wherein the training data includes a set of source code files for training a multi-representational learning (MRL) model for classifying malicious source code and benign source code based on a static analysis; generating a first feature vector based on a set of characters extracted from the set of source code files; generating a second feature vector based on a set of tokens extracted from the set of source code files; and performing an ensemble of the first feature vector and the second feature vector to form a target feature vector for classifying malicious source code and benign source code based on the static analysis.

Abstract: A spin-transfer torque magnetic random access memory (STTMRAM) element employed to store a state based on the magnetic orientation of a free layer, the STTMRAM element is made of a first perpendicular free layer (PFL) including a first perpendicular enhancement layer (PEL). The first PFL is formed on top of a seed layer. The STTMRAM element further includes a barrier layer formed on top of the first PFL and a second perpendicular reference layer (PRL) that has a second PEL. The second PRL is formed on top of the barrier layer. The STTMRAM element further includes a capping layer that is formed on top of the second PRL.

Abstract: A magnetic device for processing biological objects including a soft magnetic center pole having a bottom end and a tapered tip end; first and second soft magnetic side poles disposed on opposite sides of the soft magnetic center pole and respectively having first and second bottom ends, the first and second soft magnetic side poles respectively having first and second top ends that bend inward toward the soft magnetic center pole with a first outward side of the first top end and a second outward side of the second top end being substantially coplanar; a magnetic flux source generating magnetic flux in the soft magnetic center pole and the first and second soft magnetic side poles; and a channel plate having a channel embedded therein and a first planar surface that is operable to be in contact with or in close proximity to the first and second outward sides.

Abstract: A system/process/computer program product for building multi-representational learning models for static analysis of source code includes receiving training data, wherein the training data includes a set of source code files for training a multi-representational learning (MRL) model for classifying malicious source code and benign source code based on a static analysis; generating a first feature vector based on a set of characters extracted from the set of source code files; generating a second feature vector based on a set of tokens extracted from the set of source code files; and performing an ensemble of the first feature vector and the second feature vector to form a target feature vector for classifying malicious source code and benign source code based on the static analysis.

Abstract: Techniques for multi-representational learning models for static analysis of source code are disclosed. In some embodiments, a system/process/computer program product for multi-representational learning models for static analysis of source code includes receiving at a networked device a set comprising one or more multi-representation learning (MRL) models for static analysis of source code; performing a static analysis of source code associated with a sample received at the network device, wherein performing the static analysis includes using at least one MRL model; and determining that the sample is malicious based at least in part on the static analysis of the source code associated with the sample and without performing dynamic analysis of the sample, and in response to determining that the sample is malicious, performing an action based on a security policy.

Abstract: An author of a malicious websites campaign (scam or phishing) likely uses a legitimate third-party service to facilitate the malicious campaign. An example includes legitimate CAPTCHA (Completely Automated Public Turing Test to Tell Computers and Humans Apart) services to conceal the malicious campaign from automated security scanners. A security service/platform can employ a detection pipeline that leverages use of CAPTCHA keys across websites of a malicious websites campaign. Websites that use CAPTCHA keys found in known malicious websites can at least be identified as suspect and communicated to firewalls.

Abstract: The current invention generally relates to apparatus and method to analyze and separate biological entities, including cells, bacteria and molecules from human blood, body tissue, body fluid and other human related biological samples. The claimed apparatus and method analyze, or detect, biological entities based on optical signals received from said entities by using optical detectors. The claimed apparatus and method further separate biological entities with using micro-actuator activated sorting devices.

Abstract: Techniques for multi-representational learning models for static analysis of source code are disclosed. In some embodiments, a system/process/computer program product for multi-representational learning models for static analysis of source code includes storing on a networked device a set comprising one or more multi-representation learning (MRL) models for static analysis of source code; performing a static analysis of source code associated with a sample received at the network device, wherein performing the static analysis includes using at least one stored MRL model; and determining that the sample is malicious based at least in part on the static analysis of the source code associated with the received sample, and in response to determining that the sample is malicious, performing an action based on a security policy.

Abstract: The current invention relates to the method and apparatus to magnetically separate biological entities with magnetic labels from a fluid sample. The claimed magnetic separation device removes biological entities with magnetic labels from its fluidic solution by using a soft-magnetic center pole with two soft-magnetic side poles. The claimed device further includes processes to dissociate entities conglomerate after magnetic separation.

Abstract: To perform pattern-based detection of malicious URLs, patterns are first generated from known URLs to build a pattern repository. A URL is first normalized and parsed, and keywords are extracted and stored in an additional repository of keywords. Tokens are then determined from the parsed URL and tags are associated with the parsed substrings. Substring text may also be replaced with general identifying information. Patterns generated from known malicious and benign URLs satisfying certain criteria are published to a pattern repository of which can be accessed during subsequent detection operations. During detection, upon identifying a request which indicates an unknown URL, the URL is parsed and tokenized to generate a pattern. The repository of malicious URL patterns is queried to determine if a matching malicious URL pattern can be identified. If a matching malicious URL pattern is identified, the URL is detected as malicious.

Abstract: Web sites are crawled using multiple browser profiles to avoid malicious cloaking. Based on web page content returned from HTTP requests using the multiple browser profiles, web sites returning substantively different content to HTTP requests for different browser profiles are identified. Web sites are further filtered by common cloaking behavior, and redirect scripts are extracted from web page content that performed cloaking. Signatures comprising tokenized versions of the redirect scripts are generated and compared to a database of known cloaking signatures. URLs corresponding to signatures having approximate matches with signatures in the database are flagged for recrawling. Recrawled URLs are verified for malicious cloaking again using HTTP requests from multiple browser profiles.

Abstract: A system automatically frames locations by detecting a user's presence within a virtual detection space. The system detects sound in the detection space and converts the sound into electrical signals. The electrical signals are converted into a digital signals at common or periodic sampling rates. The system identifies speech segments in the digital signals and attenuates noise like components within or adjacent to them. The system identifies the physical locations of a speech source generating the speech segments and automatically adjusts a camera framing based on the estimated location of the active speech source generating the speech segments.

Abstract: A system automatically controls an electronic device's audio by detecting an active sound source presence within an auditory detection space. The system transitions the electronic device to selectively output a desired sound when the active sound source presence is detected and detects sound in the auditory detection space. The system enhances sound and transforms it into electrical signals. The system converts the electrical signals into a digital signal and identifies active sound segments in the digital signals. The system attenuates noise components in the digital signals and locates the physical location of the active sound source. It adjusts an output automatically by muting a second sound source in a second detection space.

Abstract: Web sites are crawled using multiple browser profiles to avoid malicious cloaking. Based on web page content returned from HTTP requests using the multiple browser profiles, web sites returning substantively different content to HTTP requests for different browser profiles are identified. Web sites are further filtered by common cloaking behavior, and redirect scripts are extracted from web page content that performed cloaking. Signatures comprising tokenized versions of the redirect scripts are generated and compared to a database of known cloaking signatures. URLs corresponding to signatures having approximate matches with signatures in the database are flagged for recrawling. Recrawled URLs are verified for malicious cloaking again using HTTP requests from multiple browser profiles.