QRASSH - A Self-Adaptive SSH Honeypot Driven by Q-Learning
Authors:
- 1 June 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 441-446
Abstract
Developed for the first time in the 80s, honeypot systems research increased tremendously in the last decade. Moving from simple monitored, emulated, Internet Services, towards intelligent systems that autonomously interact with attackers, was a normal engagement in the context of higher development of artificial intelligence as science. In this paper we present a newly developed SSH self-adaptive honeypot system that uses a Deep Q-Learning algorithm in order to decide how to interact with external attackers. The honeypot system is developed in Python and integrates an existing implementation of a Reinforcement Learning algorithm that makes use of neural network (NN).Keywords
This publication has 13 references indexed in Scilit:
- Strategic Honeypot Game Model for Distributed Denial of Service Attacks in the Smart GridIEEE Transactions on Smart Grid, 2017
- Advanced Persistent Threat: New analysis driven by life cycle phases and their challenges2016
- A game theoretic model for enabling honeypots in IoT networks2016
- Advanced persistent threats: Behind the scenes2016
- Taxonomy of honeynet solutions2015
- Human-level control through deep reinforcement learningNature, 2015
- Threat prediction using honeypot and machine learning2015
- Machine actionable indicators of compromise2014
- RASSH - Reinforced adaptive SSH honeypot2014
- A game theoretic investigation for high interaction honeypots2012