Machine Learning for Malware Detection

← Back to document page

Machine Learning for Malware DetectionLearn more on #bringonthefutureContentsBasic approaches to Malware Detection 1Machine Learning : concepts and definitions 2Unsupervised Learning 2Supervised Learning 2Deep Learning 3Machine Learning application specifics in cybersecurity 4Large representative datasets are required 4The trained model has to be interpretable 4False positive rates must be extremely low 4Algorithms must allow us to quickly adapt them to Malware writers counteractions 5Kaspersky Lab Machine Learning application 6Detecting new Malware in pre-execution with similarity hashing 6Two-stage pre-execution Detection on users computers with similarity hash mapping combined with decision trees ensemble 8Deep Learning against rare attacks 10Deep Learning in post-execution behavior Detection 10Applications in the infrastructure 12Clustering the incoming stream of objects 12Distillation.

quality of the machine learning model impacts the user system performance and its state. Because of this, machine learning-based malware detection has specifics. It is important to emphasize the data-driven nature of this approach. A created model depends heavily on the data it has seen during the training phase to

  System, Detection