Promoting or hindering: Stealthy black-box attacks against drl-based traffic signal control
Numerous studies have demonstrated, in-depth, the vulnerability of the deep reinforcement
learning (DRL) model's elements (eg, reward), which is a factor limiting the widespread …
learning (DRL) model's elements (eg, reward), which is a factor limiting the widespread …
Reinforcement learning-driven attack on road traffic signal controllers
NS Arabi, T Halabi, M Zulkernine - 2021 IEEE International …, 2021 - ieeexplore.ieee.org
Intelligent Transportation Systems (ITS) combine emerging communication, computer, and
system technologies to deliver intelligent road traffic services and optimize decision making …
system technologies to deliver intelligent road traffic services and optimize decision making …
Adversarial Attacks on Deep Reinforcement Learning-based Traffic Signal Control Systems with Colluding Vehicles
The rapid advancements of Internet of Things (IoT) and Artificial Intelligence (AI) have
catalyzed the development of adaptive traffic control systems (ATCS) for smart cities. In …
catalyzed the development of adaptive traffic control systems (ATCS) for smart cities. In …
Manipulating reinforcement learning: Stealthy attacks on cost signals
Reinforcement learning (RL) is a powerful paradigm for online decision-making in unknown
environment. Recently, many advanced RL algorithms have been developed and applied to …
environment. Recently, many advanced RL algorithms have been developed and applied to …
Attacking deep reinforcement learning with decoupled adversarial policy
While Deep Reinforcement Learning (DRL) has achieved outstanding performance in
extensive applications, exploiting its vulnerability with adversarial attacks is essential …
extensive applications, exploiting its vulnerability with adversarial attacks is essential …
Adversarial attacks and defense in deep reinforcement learning (DRL)-based traffic signal controllers
Security attacks on intelligent transportation systems (ITS) may result in life-threatening
situations. Combining deep neural networks with reinforcement learning (RL) models called …
situations. Combining deep neural networks with reinforcement learning (RL) models called …
The faults in our pi stars: Security issues and open challenges in deep reinforcement learning
V Behzadan, A Munir - arXiv preprint arXiv:1810.10369, 2018 - arxiv.org
Since the inception of Deep Reinforcement Learning (DRL) algorithms, there has been a
growing interest in both research and industrial communities in the promising potentials of …
growing interest in both research and industrial communities in the promising potentials of …
A trigger exploration method for backdoor attacks on deep learning-based traffic control systems
Y Wang, M Maniatakos… - 2021 60th IEEE …, 2021 - ieeexplore.ieee.org
Deep learning methods are in the forefront of techniques used to perform complex controls
in autonomous vehicles (AVs). Such methods are vulnerable to nuanced types of …
in autonomous vehicles (AVs). Such methods are vulnerable to nuanced types of …
Stop-and-go: Exploring backdoor attacks on deep reinforcement learning-based traffic congestion control systems
Recent work has shown that the introduction of autonomous vehicles (AVs) in traffic could
help reduce traffic jams. Deep reinforcement learning methods demonstrate good …
help reduce traffic jams. Deep reinforcement learning methods demonstrate good …
Backdoor attacks against deep reinforcement learning based traffic signal control systems
To improve the efficiency of the traffic signal control and alleviate traffic congestion, many
researchers focus on applying deep reinforcement learning (DRL) for traffic signal control …
researchers focus on applying deep reinforcement learning (DRL) for traffic signal control …