Cyber Security Lab

Current Research Topics

Lab Research Team

Securing keystrokes:
  1. Securing keystroke dynamics from replay attacks

  2. Keystroke dynamics obfuscation using key grouping

Black-box end-to-end attacks/security
  1. Defense methods against adversarial examples for recurrent neural networks

  2. Low resource black-box end-to-end attack against state of the art API call based malware classifiers

  3. Generic black-box end-to-end attack against rnns and other api calls based malware classifiers

  4. Query-efficient gan based black-box attack against sequence based machine and deep learning classifiers

  5. Query-Efficient Black-Box Attack Against Sequence-Based Malware Classifiers

Effective Database Activity Monitoring:
  1. Using Bandits for Effective Database Activity Monitoring

  2. Diversifying database activity monitoring with bandits

  3. Simulating user activity for assessing effect of sampling on DB activity monitoring anomaly detection

  4. Sampling high throughput data for anomaly detection of data-base activity

  5. CyberRank: knowledge elicitation for risk assessment of database security

© 2020 ML-Labs BGU-SISE

  • Facebook
  • Linkedin