TY - GEN
T1 - Fooling Edge Computation Offloading via Stealthy Interference Attack
AU - Zhang, Letian
AU - Xu, Jie
N1 - Funding Information:
This work is supported in part by the Army Research Office under award W911NF-18-1-0343 and by the National Science Foundation under awards 2029858, 2033681 and 2006630.
Publisher Copyright:
© 2020 IEEE.
Copyright:
Copyright 2021 Elsevier B.V., All rights reserved.
PY - 2020/11
Y1 - 2020/11
N2 - There is a growing interest in developing deep learning methods to solve many resource management problems in wireless edge computing systems where model-based designs are infeasible. While deep learning is known to be vulnerable to adversarial example attacks, the security risk of learningbased designs in the context of edge computing is not well understood. In this paper, we propose and study a new adversarial example attack, called stealthy interference attack (SIA), in deep reinforcement learning (DRL)-based edge computation offloading systems. In SIA, the attacker exerts a carefully determined level of interference signal to change the input states of the DRL-based policy, thereby fooling the mobile device in selecting a target and compromised edge server for computation offloading while evading detection. Simulation results demonstrate the effectiveness of SIA, and show that our algorithm outperforms existing adversarial machine learning algorithms in terms of a higher attack success probability and a lower power consumption.
AB - There is a growing interest in developing deep learning methods to solve many resource management problems in wireless edge computing systems where model-based designs are infeasible. While deep learning is known to be vulnerable to adversarial example attacks, the security risk of learningbased designs in the context of edge computing is not well understood. In this paper, we propose and study a new adversarial example attack, called stealthy interference attack (SIA), in deep reinforcement learning (DRL)-based edge computation offloading systems. In SIA, the attacker exerts a carefully determined level of interference signal to change the input states of the DRL-based policy, thereby fooling the mobile device in selecting a target and compromised edge server for computation offloading while evading detection. Simulation results demonstrate the effectiveness of SIA, and show that our algorithm outperforms existing adversarial machine learning algorithms in terms of a higher attack success probability and a lower power consumption.
UR - http://www.scopus.com/inward/record.url?scp=85102184770&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85102184770&partnerID=8YFLogxK
U2 - 10.1109/SEC50012.2020.00062
DO - 10.1109/SEC50012.2020.00062
M3 - Conference contribution
AN - SCOPUS:85102184770
T3 - Proceedings - 2020 IEEE/ACM Symposium on Edge Computing, SEC 2020
SP - 415
EP - 419
BT - Proceedings - 2020 IEEE/ACM Symposium on Edge Computing, SEC 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 5th IEEE/ACM Symposium on Edge Computing, SEC 2020
Y2 - 11 November 2020 through 13 November 2020
ER -