POMDPs Make Better Hackers: Accounting for Uncertainty in Penetration Testing

TL;DR

This paper introduces a POMDP-based approach to penetration testing that models uncertainty and employs intelligent scanning, resulting in more effective and scalable attack planning on networks.

Contribution

It presents a novel POMDP formulation for attack planning that incorporates uncertainty and scanning actions, with a scalable decomposition method for network-wide attacks.

Findings

Effective in runtime and solution quality on industrial test suite

Utilizes network structure for attack decomposition

Balances accuracy and scalability in attack planning

Abstract

Penetration Testing is a methodology for assessing network security, by generating and executing possible hacking attacks. Doing so automatically allows for regular and systematic testing. A key question is how to generate the attacks. This is naturally formulated as planning under uncertainty, i.e., under incomplete knowledge about the network configuration. Previous work uses classical planning, and requires costly pre-processes reducing this uncertainty by extensive application of scanning methods. By contrast, we herein model the attack planning problem in terms of partially observable Markov decision processes (POMDP). This allows to reason about the knowledge available, and to intelligently employ scanning actions as part of the attack. As one would expect, this accurate solution does not scale. We devise a method that relies on POMDPs to find good attacks on individual machines, which are then composed into an attack on the network as a whole. This decomposition exploits network structure to the extent possible, making targeted approximations (only) where needed. Evaluating this method on a suitably adapted industrial test suite, we demonstrate its effectiveness in both runtime and solution quality.