Sensitivity of Dynamic Network Slicing to Deep Reinforcement Learning Based Jamming Attacks
- Resource Type
- Conference
- Authors
- Wang, Feng; Gursoy, M. Cenk; Velipasalar, Senem
- Source
- 2023 IEEE 34th Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC) Personal, Indoor and Mobile Radio Communications (PIMRC), 2023 IEEE 34th Annual International Symposium on. :1-6 Sep, 2023
- Subject
- Communication, Networking and Broadcast Technologies
Computing and Processing
Robotics and Control Systems
Signal Processing and Analysis
Knowledge engineering
Deep learning
Network slicing
Simulation
Channel estimation
Reinforcement learning
Interference
dynamic channel access
deep reinforcement learning
multi-agent actor-critic
adversarial learning
jamming attacks
- Language
- ISSN
- 2166-9589
In this paper, we consider multi-agent deep reinforcement learning (deep RL) based network slicing agents in a dynamic environment with multiple base stations and multiple users. We develop a deep RL based jammer with limited prior information and limited power budget. The goal of the jammer is to minimize the transmission rates achieved with network slicing and thus degrade the network slicing agents’ performance. We design a jammer with both listening and jamming phases and address jamming location optimization as well as jamming channel optimization via deep RL. We evaluate the jammer at the optimized location, generating interference attacks in the optimized set of channels by switching between the jamming phase and listening phase. We show that the proposed jammer can significantly reduce the victims’ performance without direct feedback or prior knowledge on the network slicing policies.