In traditional machine learning, the learning process is supervised, and the programmer has to be extremely specific when telling the computer what types of things it should be looking for. This process, called “feature extraction” can be laborious, and the computer’s success rate depends entirely upon the programmer’s ability to accurately define a feature. The advantage of deep learning is the program builds the feature set by itself without supervision. Tech Talks brought this news to us in their article, “Computer vision and deep learning provide new ways to detect cyber threats.”
When attempting to detect malware, the traditional way is to search files for known signatures of malicious payloads. Malware developers can easily circumvent such detection methods. Research has shown that deep learning models were especially good at detecting malware in .doc and .pdf files, which are the preferred medium for ransomware attacks.
Data Harmony is Access Innovations’ AI suite of tools that leverage explainable AI for efficient, innovative and precise semantic discovery of new and emerging concepts to help find the information you need when you need it.
Melody K. Smith
Sponsored by Access Innovations, the intelligence and the technology behind world-class explainable AI solutions.
