Mitigation of Policy Manipulation Attacks on Deep Q-Networks with Parameter-Space Noise

06/04/2018
by   Vahid Behzadan, et al.
0

Recent developments have established the vulnerability of deep reinforcement learning to policy manipulation attacks via intentionally perturbed inputs, known as adversarial examples. In this work, we propose a technique for mitigation of such attacks based on addition of noise to the parameter space of deep reinforcement learners during training. We experimentally verify the effect of parameter-space noise in reducing the transferability of adversarial examples, and demonstrate the promising performance of this technique in mitigating the impact of whitebox and blackbox attacks at both test and training times.

READ FULL TEXT
research
01/16/2017

Vulnerability of Deep Reinforcement Learning to Policy Induction Attacks

Deep learning classifiers are known to be inherently vulnerable to manip...
research
12/23/2017

Whatever Does Not Kill Deep Reinforcement Learning, Makes It Stronger

Recent developments have established the vulnerability of deep Reinforce...
research
05/18/2017

Delving into adversarial attacks on deep policies

Adversarial examples have been shown to exist for a variety of deep lear...
research
09/18/2018

Switching Isotropic and Directional Exploration with Parameter Space Noise in Deep Reinforcement Learning

This paper proposes an exploration method for deep reinforcement learnin...
research
02/22/2022

A Comparative Study of Deep Reinforcement Learning-based Transferable Energy Management Strategies for Hybrid Electric Vehicles

The deep reinforcement learning-based energy management strategies (EMS)...
research
06/01/2020

Adversarial Attacks on Reinforcement Learning based Energy Management Systems of Extended Range Electric Delivery Vehicles

Adversarial examples are firstly investigated in the area of computer vi...
research
09/29/2021

Mitigation of Adversarial Policy Imitation via Constrained Randomization of Policy (CRoP)

Deep reinforcement learning (DRL) policies are vulnerable to unauthorize...

Please sign up or login with your details

Forgot password? Click here to reset