Intrusion Prevention System based on Machine Learning

Transcript

1. Intrusion Prevention System based on Machine Learning Hendri Karisma; Raden Ardiansyah Natakusumah Hackathon #2 - December 20-21st, 2016
2. Background • Promo to gather/increase customer • Increasing Traffic = increasing threat • Legitimate vs malicious • Malicious  disrupt promo target • Preventive: filter traffic based on behaviour
3. Intrusion Prevention System • Intrusion prevention is the process of performing intrusion detection and attempting to stop detected possible incidents. • The main functions of intrusion prevention systems are to identify malicious activity, log information about this activity, attempt to block/stop it, and report it.
4. Machine Learning • Machine learning is the subfield of computer science that "gives computers the ability to learn without being explicitly programmed" Source: Arthur Samuel, 1959 Image source: Coursera, Machine Learning
5. Flow Architecture Machine Learning Web Application Firewall IPS blibli.com INTERNET MALICIOUS LEGITIMATE
6. Benefits PROFIT Increase Customer Legitimate traffic Reduce malicious
7. Machine Learning in e-Commerce • Fraud Prevention • Intelligent Customer-service Chatbots • Improve product search • Recommendation (you may like ...) • Merchandising (this item goes with this item) • Sentiment and trend analysis • Shipping cost and time estimation • Inbound and outbound logistic optimization • Entity resolution (do these three accounts belong to the same person?) • Market right pricing • Supply and demand analysis and forecast • ... Source: Farhang Kassaei, Engineering Director at Google