Reinforcement learning (RL) for network slicing is considered in the 5G radio access network, where the base station, gNodeB, allocates resource blocks (RBs) to the requests of user equipments and maximizes the total reward of accepted requests over time. Based on adversarial machine learning, a novel over-the-air attack is introduced to manipulate the RL algorithm and disrupt 5G network slicing. Subject to an energy budget, the adversary observes the spectrum and builds its own RL-based surrogate model that selects which RBs to jam with the objective of maximizing the number of failed network slicing requests due to jammed RBs. By jamming the RBs, the adversary reduces the RL algorithms reward. As this reward is used as the input to update the RL algorithm, the performance does not recover even after the adversary stops jamming. This attack is evaluated in terms of the recovery time and the (maximum and total) reward loss, and it is shown to be much more effective than benchmark (random and myopic) jamming attacks. Different reactive and proactive defense mechanisms (protecting the RL algorithms updates or misleading the adversarys learning process) are introduced to show that it is viable to defend 5G network slicing against this attack.
تحميل البحث