Mcafee, Inc.

Fireeye, Inc.

Rahul Mohandas

Vinoo Thomas

Palasamudram Ramagopal Prashanth

Jayesh Kandappamkattil Sreedharan

Santhosh Kumar Ramachandran

Balamurugan Rajagopalan

Vamshi Kumar Kurva

Plasamudram Ramagopal Prashanth

The presently disclosed subject matter includes a system for the detection of phishing cyber-attacks based on an application of deep machine learning techniques including the implementation of a deep convolutional neural network to determine whether a web element associated with a uniform resource locator is part of a phishing cyber-attack. The system produces a notification indicative of the phishing cyber-attack when a positive match between the uniform resource locator and the phishing cyber-attack is determined. The convolutional neural network is retrained at periodic time intervals with new datasets retrieved by an automated dataset collector and thus, improves the detection of zero-days cyber-attacks.

System and method for identifying phishing cyber-attacks through deep machine learning via a convolutional neural network (CNN) engine

A system, method, and computer program product are provided for identifying a file utilized to automatically launch content as unwanted. In one embodiment, a file is identified in response to a detection of unwanted code, the file utilized to automatically launch content. Additionally, it is determined whether an identifier associated with the unwanted code is included in the file. Further, the file is identified as unwanted based on the determination.

System, method, and computer program product for identifying a file used to automatically launch content as unwanted

Methods and systems for risk rating and pro-actively detecting malicious online ads are described. In one example embodiment, a system for risk rating and pro-actively detecting malicious online ads includes an extraction module, an analysis engine, and a filter module. The extraction module is configured to extract a SWF file from a web page downloaded by the system. The analysis engine is communicatively coupled to the extraction module. The analysis engine is configured to determine a risk rating for the SWF file and send the risk rating to a web application for display. In an example, determining the risk rating includes locating an embedded redirection URL and determining a risk rating for the embedded redirection URL. The filter module is configured to determine, based on the risk rating, whether to block the SWF file and send a warning to the web application for display.

Systems and methods for risk rating and pro-actively detecting malicious online ads

Systems and method to detect malicious media file are described. In one example, an apparatus including a network connection, a memory, and a programmable processor communicatively coupled to the memory is discussed. The memory can include instructions, which when executed by the programmable processor cause the apparatus to receive a data stream from the network connection and detect at least a portion of a media file within the data stream. The instructions can also cause the apparatus to determine a file type of the media file and extract the media file from the data stream. Further, the instructions cause the apparatus to parse the media file to location a suspicious tag, extract an embedded URL from the suspicious tag, determine with the embedded URL is malicious, and block the media file if the embedded URL is malicious.

Growing community of inventors

Bengaluru, India

Rahul Mohandas