Image and Video Forensics
Mayachitra team is developing state-of-the-art methods for media forensics (supported by the DARPA MediFOR program, and in collaboration with researchers at the China Lake Air Warfare Research Center and the University of California, Riverside). The developed methods will be able to differentiate between manipulated and un-manipulated images, and localize the manipulated regions. These methods leverage recent advances in deep learning for image analysis with the team’s expertise in image processing, segmentation and classification.
New approaches for Malware Detection and Classification
Researchers at Mayachitra are pioneering new ways of detecting and classifying computer malware. A new malware detection/classification system, called MalSee, is deployed as a web-accessible service. Mayachitra’s unique technology empowers robust and fast detection of harmful computer viruses, offering ~1000x speedup compared to existing methods. The solution leverages on ideas from signal processing, pattern recognition, and deep learning. This project is currently being supported by a Phase II Navy SBIR funding. The developed algorithms utilizes resources and malware samples from various sources including UCSB Vision Research Lab, UCSB Seclab, VirusShare, VirusTotal and VirusSamples.
