Autonomous Security Analysis and Penetration Testing
Authors:
- 1 December 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 508-515
Abstract
Security Assessment of large networks is a challenging task. Penetration testing (pentesting) is a method of analyzing the attack surface of a network to find security vulnerabilities. Current network pentesting techniques involve a combination of automated scanning tools and manual exploitation of security issues to identify possible threats in a network. The solution scales poorly on a large network. We propose an autonomous security analysis and penetration testing framework (ASAP) that creates a map of security threats and possible attack paths in the network using attack graphs. Our framework utilizes: (i) state of the art reinforcement learning algorithm based on Deep-Q Network (DQN) to identify optimal policy for performing pentesting testing, and (ii) incorporates domain-specific transition matrix and reward modeling to capture the importance of security vulnerabilities and difficulty inherent in exploiting them. ASAP framework generates autonomous attack plans and validates them against real-world networks. The attack plans are generalizable to complex enterprise network, and the framework scales well on a large network. Our empirical evaluation shows that ASAP identifies non-intuitive attack plans on an enterprise network. The DQN planning algorithm employed scales well on a large network $\sim 60 -70(\mathrm{s})$ for generating an attack plan for network with 300 hosts.
Keywords
This publication has 17 references indexed in Scilit:
- Introduction to PyTorch2017
- SDN based Scalable MTD solution in Cloud Network2016
- Human-level control through deep reinforcement learningNature, 2015
- NICE: Network Intrusion Detection and Countermeasure Selection in Virtual Network SystemsIEEE Transactions on Dependable and Secure Computing, 2013
- An algorithm to find optimal attack paths in nondeterministic scenarios2011
- An analysis of CVSS version 2 vulnerability scoring2009
- Common Vulnerability Scoring SystemIEEE Security & Privacy, 2006
- A scalable approach to attack graph generation2006
- Reinforcement Learning: A SurveyJournal of Artificial Intelligence Research, 1996
- Q-learningMachine Learning, 1992