MalSee, developed by Mayachitra, Inc., employs novel machine learning and computer vision based multi-tiered strategy to thwart cyber-attacks. MalSee is computationally efficient, has a compact memory footprint, and can identify computer viruses across different platforms such as Windows, MacOS, Android, iOS, to provide security against known and zero-day attacks.

The algorithm involves visualizing a query binary file as a 1D/2D signal and extracting signal-based orthogonal features for comparison of similar features in the database, and further providing one of the three (benign/ambiguous/malware) prediction labels to determine its maliciousness.

Recent Publications

• Tajuddin Manhar Mohammed, Lakshmanan Nataraj, Satish Chikkagoudar, Shivkumar Chandrasekaran, B. S. Manjunath, "MalGrid: Visualization Of Binary Features In Large Malware Corpora", IEEE Military Communications Conference (MILCOM), 2022.
  [paper]

• Lakshmanan Nataraj, Tajuddin Manhar Mohammed, Tejaswi Nanjundaswamy, Satish Chikkagoudar, Shivkumar Chandrasekaran, B. S. Manjunath, "OMD: Orthogonal Malware Detection Using Audio, Image, and Static Features", IEEE Military Communications Conference (MILCOM), 2021.
  [paper]

• Tajuddin Manhar Mohammed, Lakshmanan Nataraj, Satish Chikkagoudar, Shivkumar Chandrasekaran, B. S. Manjunath, "HAPSSA: Holistic Approach to PDF Malware Detection Using Signal and Statistical Analysis", IEEE Military Communications Conference (MILCOM), 2021.
  [paper]

• Tajuddin Manhar Mohammed, Lakshmanan Nataraj, Satish Chikkagoudar, Shivkumar Chandrasekaran, B. S. Manjunath, "Malware Detection Using Frequency Domain-Based Image Visualization and Deep Learning", Proceedings of the 54th Hawaii International Conference on System Sciences (HICSS), 2021.
  [paper]

• Lakshmanan Nataraj, B. S. Manjunath, "SPAM: Signal Processing to Analyze Malware", IEEE SIgnal ProcESSIng MagazInE, 2016.
  [paper]

Patents

• Tajuddin Manhar Mohammed, Lakshmanan Nataraj, B. S. Manjunath, Shivkumar Chandrasekaran, "Malware detection using frequency domain-based image visualization and deep learning", U.S. Patent (pending), published September 29, 2022.
  [full text]

• Lakshmanan Nataraj, B. S. Manjunath, Shivkumar Chandrasekaran, "Malware classification and detection using audio descriptors", U.S. Patent Number 11,244,050, issued February 8, 2022.
  [full text]

Malware Datasets

• MaleX - The MaleX Dataset is a curated dataset that contains 1,044,394 Windows executable binaries and its image representations with 864,669 labelled as malware and 179,725 as benign (only images are made available at this time).
• MalImg - The MalImg Dataset contains 9,339 malware images that belongs to 25 different malware families.