Adversarial Deep Reinforcement Learning for Cyber Security in Software Defined Networks

This paper focuses on the impact of leveraging autonomous offensive approaches in Deep Reinforcement Learning (DRL) to train more robust agents by exploring the impact of applying adversarial learning to DRL for autonomous security in Software Defined Networks (SDN). Two algorithms, Double Deep Q-Networks (DDQN) and Neural Episodic Control to Deep Q-Network (NEC2DQN or N2D), are compared. NEC2DQN was proposed in 2018 and is a new member of the deep q-network (DQN) family of algorithms. The attacker has full observability of the environment and access to a causative attack that uses state manipulation in an attempt to poison the learning process. The implementation of the attack is done under a white-box setting, in which the attacker has access to the defender's model and experiences. Two games are played; in the first game, DDQN is a defender and N2D is an attacker, and in second game, the roles are reversed. The games are played twice; first, without an active causative attack and secondly, with an active causative attack. For execution, three sets of game results are recorded in which a single set consists of 10 game runs. The before and after results are then compared in order to see if there was actually an improvement or degradation. The results show that with minute parameter changes made to the algorithms, there was growth in the attacker's role, since it is able to win games. Implementation of the adversarial learning by the introduction of the causative attack showed the algorithms are still able to defend the network according to their strengths.

Model-Free Deep Reinforcement Learning in Software-Defined Networks

This paper compares two deep reinforcement learning approaches for cyber security in software defined networking. Neural Episodic Control to Deep Q-Network has been implemented and compared with that of Double Deep Q-Networks. The two algorithms are implemented in a format similar to that of a zero-sum game. A two-tailed T-test analysis is done on the two game results containing the amount of turns taken for the defender to win. Another comparison is done on the game scores of the agents in the respective games. The analysis is done to determine which algorithm is the best in game performer and whether there is a significant difference between them, demonstrating if one would have greater preference over the other. It was found that there is no significant statistical difference between the two approaches.