Pasquale Malacaria

Marcello De Bernardi, MHR Khouzani, Pasquale Malacaria

Pseudo-random number generators (PRNG) are a fundamental element of many security algorithms. We introduce a novel approach to their implementation, by proposing the use of generative adversarial networks (GAN) to train a neural network to behave as a PRNG. Furthermore, we showcase a number of interesting modifications to the standard GAN architecture. The most significant is partially concealing the output of the GAN's generator, and training the adversary to discover a mapping from the overt part to the concealed part. The generator therefore learns to produce values the adversary cannot predict, rather than to approximate an explicit reference distribution. We demonstrate that a GAN can effectively train even a small feed-forward fully connected neural network to produce pseudo-random number sequences with good statistical properties. At best, subjected to the NIST test suite, the trained generator passed around 99% of test instances and 98% of overall tests, outperforming a number of standard non-cryptographic PRNGs.

Andrew Fielder, Emmanouil Panaousis, Pasquale Malacaria et al.

When investing in cyber security resources, information security managers have to follow effective decision-making strategies. We refer to this as the cyber security investment challenge. In this paper, we consider three possible decision-support methodologies for security managers to tackle this challenge. We consider methods based on game theory, combinatorial optimisation and a hybrid of the two. Our modelling starts by building a framework where we can investigate the effectiveness of a cyber security control regarding the protection of different assets seen as targets in presence of commodity threats. In terms of game theory we consider a 2-person control game between the security manager who has to choose among different implementation levels of a cyber security control, and a commodity attacker who chooses among different targets to attack. The pure game theoretical methodology consists of a large game including all controls and all threats. In the hybrid methodology the game solutions of individual control-games along with their direct costs (e.g. financial) are combined with a knapsack algorithm to derive an optimal investment strategy. The combinatorial optimisation technique consists of a multi-objective multiple choice knapsack based strategy. We compare these approaches on a case study that was built on SANS top critical controls. The main achievements of this work is to highlight the weaknesses and strengths of different investment methodologies for cyber security, the benefit of their interaction, and the impact that indirect costs have on cyber security investment.