Reinforcement Learning based Cyberattack Model for Adaptive Traffic Signal Controller in Connected Transportation Systems

no code implementations • 31 Oct 2022 • Muhammad Sami Irfan, Mizanur Rahman, Travis Atkison, Sagar Dasgupta, Alexander Hainen

Specifically, an RL agent is trained to learn an optimal rate of sybil vehicle injection to create congestion for an approach(s).

An Innovative Attack Modelling and Attack Detection Approach for a Waiting Time-based Adaptive Traffic Signal Controller

no code implementations • 19 Aug 2021 • Sagar Dasgupta, Courtland Hollis, Mizanur Rahman, Travis Atkison

Thus, the objectives of this paper are to: (i) develop a "slow poisoning" attack generation strategy for an ATSC, and (ii) develop a prediction-based "slow poisoning" attack detection strategy using a recurrent neural network -- i. e., long short-term memory model.