Learning Attacker's Bounded Rationality Model in Security Games

TL;DR

This paper introduces NESG, a neuroevolutionary approach utilizing SENN to evaluate strategies in security games with bounded rationality, outperforming existing methods especially against irrational opponents.

Contribution

The paper presents a novel, knowledge-free neuroevolutionary method (NESG) with SENN for security games, capable of handling bounded rationality without prior opponent knowledge.

Findings

Outperforms state-of-the-art methods in benchmark cybersecurity scenarios

Provides high-quality solutions with scalable computation time

Effective against opponents with cognitive biases or irrational behavior

Abstract

The paper proposes a novel neuroevolutionary method (NESG) for calculating leader's payoff in Stackelberg Security Games. The heart of NESG is strategy evaluation neural network (SENN). SENN is able to effectively evaluate leader's strategies against an opponent who may potentially not behave in a perfectly rational way due to certain cognitive biases or limitations. SENN is trained on historical data and does not require any direct prior knowledge regarding the follower's target preferences, payoff distribution or bounded rationality model. NESG was tested on a set of 90 benchmark games inspired by real-world cybersecurity scenario known as deep packet inspections. Experimental results show an advantage of applying NESG over the existing state-of-the-art methods when playing against not perfectly rational opponents. The method provides high quality solutions with superior computation time scalability. Due to generic and knowledge-free construction of NESG, the method may be applied to various real-life security scenarios.