Examining Machine Learning for 5G and Beyond Through an Adversarial Lens

Spurred by the recent advances in deep learning to harness rich information hidden in large volumes of data and to tackle problems that are hard to model/solve (e.g., resource allocation problems), there is currently tremendous excitement in the mobile networks domain around the transformative potential of data-driven AI/ML based network automation, control and analytics for 5G and beyond. In this article, we present a cautionary perspective on the use of AI/ML in the 5G context by highlighting the adversarial dimension spanning multiple types of ML (supervised/unsupervised/RL) and support this through three case studies. We also discuss approaches to mitigate this adversarial ML risk, offer guidelines for evaluating the robustness of ML models, and call attention to issues surrounding ML oriented research in 5G more generally.

[1]  Fabio Roli,et al.  Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning , 2017, Pattern Recognit..

[2]  Junaid Qadir,et al.  Black-box Adversarial Machine Learning Attack on Network Traffic Classification , 2019, 2019 15th International Wireless Communications & Mobile Computing Conference (IWCMC).

[3]  Timothy J. O'Shea,et al.  Radio Machine Learning Dataset Generation with GNU Radio , 2016 .

[4]  Junaid Qadir,et al.  The Adversarial Machine Learning Conundrum: Can the Insecurity of ML Become the Achilles' Heel of Cognitive Networks? , 2019, IEEE Network.

[5]  Hao Chen,et al.  Artificial Intelligence-Enabled Cellular Networks: A Critical Path to Beyond-5G and 6G , 2019, IEEE Wireless Communications.

[6]  Aleksander Madry,et al.  On Evaluating Adversarial Robustness , 2019, ArXiv.

[7]  David A. Wagner,et al.  Towards Evaluating the Robustness of Neural Networks , 2016, 2017 IEEE Symposium on Security and Privacy (SP).

[8]  Guan Gui,et al.  Deep Learning for Super-Resolution Channel Estimation and DOA Estimation Based Massive MIMO System , 2018, IEEE Transactions on Vehicular Technology.

[9]  Yi Shi,et al.  When Wireless Security Meets Machine Learning: Motivation, Challenges, and Research Directions , 2020, ArXiv.

[10]  Joan Bruna,et al.  Intriguing properties of neural networks , 2013, ICLR.

[11]  Mahesh K. Marina,et al.  Iris: Deep Reinforcement Learning Driven Shared Spectrum Access Architecture for Indoor Neutral-Host Small Cells , 2018, IEEE Journal on Selected Areas in Communications.

[12]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.

[13]  Yishay Mansour,et al.  Policy Gradient Methods for Reinforcement Learning with Function Approximation , 1999, NIPS.

[14]  Dinh Thai Hoang,et al.  Challenges and Countermeasures for Adversarial Attacks on Deep Reinforcement Learning , 2020, IEEE Transactions on Artificial Intelligence.

[15]  Akihiro Nakao,et al.  Challenges in Resource Allocation in Network V irtualization , 2009 .

[16]  Ananthram Swami,et al.  The Limitations of Deep Learning in Adversarial Settings , 2015, 2016 IEEE European Symposium on Security and Privacy (EuroS&P).

[17]  Jakob Hoydis,et al.  Deep Reinforcement Learning Autoencoder with Noisy Feedback , 2018, 2019 International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOPT).

[18]  Andrei Gurtov,et al.  Security for 5G and Beyond , 2019, IEEE Communications Surveys & Tutorials.

[19]  Junaid Qadir,et al.  Securing Connected & Autonomous Vehicles: Challenges Posed by Adversarial Machine Learning and the Way Forward , 2019, IEEE Communications Surveys & Tutorials.

[20]  Lenan Wu,et al.  Automatic Modulation Classification: A Deep Learning Enabled Approach , 2018, IEEE Transactions on Vehicular Technology.

[21]  Jakob Hoydis,et al.  An Introduction to Deep Learning for the Physical Layer , 2017, IEEE Transactions on Cognitive Communications and Networking.

[22]  Kiran Karra,et al.  Learning to communicate: Channel auto-encoders, domain specific regularizers, and attention , 2016, 2016 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT).

[23]  Siddique Latif,et al.  Generative Adversarial Networks For Launching and Thwarting Adversarial Attacks on Network Intrusion Detection Systems , 2019, 2019 15th International Wireless Communications & Mobile Computing Conference (IWCMC).