A Temporal-Pattern Backdoor Attack to Deep Reinforcement Learning

by   Yinbo Yu, et al.
China Unicom Limited

Deep reinforcement learning (DRL) has made significant achievements in many real-world applications. But these real-world applications typically can only provide partial observations for making decisions due to occlusions and noisy sensors. However, partial state observability can be used to hide malicious behaviors for backdoors. In this paper, we explore the sequential nature of DRL and propose a novel temporal-pattern backdoor attack to DRL, whose trigger is a set of temporal constraints on a sequence of observations rather than a single observation, and effect can be kept in a controllable duration rather than in the instant. We validate our proposed backdoor attack to a typical job scheduling task in cloud computing. Numerous experimental results show that our backdoor can achieve excellent effectiveness, stealthiness, and sustainability. Our backdoor's average clean data accuracy and attack success rate can reach 97.8


page 1

page 2

page 3

page 4


A New Approach for Resource Scheduling with Deep Reinforcement Learning

With the rapid development of deep learning, deep reinforcement learning...

Effective Multi-User Delay-Constrained Scheduling with Deep Recurrent Reinforcement Learning

Multi-user delay constrained scheduling is important in many real-world ...

Don't Watch Me: A Spatio-Temporal Trojan Attack on Deep-Reinforcement-Learning-Augment Autonomous Driving

Deep reinforcement learning (DRL) is one of the most popular algorithms ...

Causal Inference Q-Network: Toward Resilient Reinforcement Learning

Deep reinforcement learning (DRL) has demonstrated impressive performanc...

Hypernetwork Dismantling via Deep Reinforcement Learning

Network dismantling aims to degrade the connectivity of a network by rem...

The Pump Scheduling Problem: A Real-World Scenario for Reinforcement Learning

Deep Reinforcement Learning (DRL) has achieved remarkable success in sce...

SoCRATES: System-on-Chip Resource Adaptive Scheduling using Deep Reinforcement Learning

Deep Reinforcement Learning (DRL) is being increasingly applied to the p...

Please sign up or login with your details

Forgot password? Click here to reset