Downlink Power Allocation in Massive MIMO via Deep Learning: Adversarial Attacks and Training
Not on the map. Why?
Abstract (arXiv)
The successful emergence of deep learning (DL) in wireless system applications has raised concerns about new security-related challenges. One such security challenge is adversarial attacks. Although there has been much work demonstrating the susceptibility of DL-based classification tasks to adversarial attacks, regression-based problems in the context of a wireless system have not been studied so far from an attack perspective. The aim of this paper is twofold: (i) we consider a regression problem in a wireless setting and show that adversarial attacks can break the DL-based approach and (ii) we analyze the effectiveness of adversarial training as a defensive technique in adversarial settings and show that the robustness of DL-based wireless system against attacks improves significantly. Specifically, the wireless application considered in this paper is the DL-based power allocation in the downlink of a multicell massive multi-input-multi-output system, where the goal of the attack is to yield an infeasible solution by the DL model. We extend the gradient-based adversarial attacks: fast gradient sign method (FGSM), momentum iterative FGSM, and projected gradient descent method to analyze the susceptibility of the considered wireless application with and without adversarial training. We analyze the deep neural network (DNN) models performance against these attacks, where the adversarial perturbations are crafted using both the white-box and black-box attacks.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 38 of its 47 references that are in the map. First posted on arXiv 14 Jun 2022.
Builds on
38 of 47 references.
References · 38
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
- 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
- 2016Adversarial Machine Learning at Scalecited by 936
- 2016Practical Black-Box Attacks against Machine Learningcited by 903
- 2014Deep Learning in Neural Networks: An Overviewcited by 770
- 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 678
- 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 546
- 2017Countering Adversarial Images using Input Transformationscited by 520
- 2020Overfitting in adversarially robust deep learningcited by 506
- 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 446
26 more
- 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 351
- 2017Detecting Adversarial Samples from Artifactscited by 245
- 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 244
- 2017On Detecting Adversarial Perturbationscited by 232
- 2019Adversarial Robustness Against the Union of Multiple Perturbation Modelscited by 88
- 2017Deep Learning-Based Communication Over the Aircited by 72
- 2015Learning with a Strong Adversarycited by 68
- 2018Adversarial Attacks on Deep-Learning Based Radio Signal Classificationcited by 47
- 2020Deep Learning for Wireless Communicationscited by 39
- 2018Attacks Meet Interpretability: Attribute-steered Detection of Adversarial Samplescited by 38
- 2018Deep Learning for Launching and Mitigating Wireless Jamming Attackscited by 31
- 2019Deep Learning for Physical-Layer 5G Wireless Techniques: Opportunities, Challenges and Solutionscited by 29
- 2019Evaluating Adversarial Evasion Attacks in the Context of Wireless Communicationscited by 28
- 2019Adversarial Deep Learning for Over-the-Air Spectrum Poisoning Attackscited by 20
- 2019Physical Adversarial Attacks Against End-to-End Autoencoder Communication Systemscited by 19
- 2017An Iterative BP-CNN Architecture for Channel Decodingcited by 18
- 2019The Best Defense Is a Good Offense: Adversarial Attacks to Avoid Modulation Detectioncited by 17
- 2018Novel Massive MIMO Channel Sounding Data Applied to Deep Learning-based Indoor Positioningcited by 16
- 2019Trojan Attacks on Wireless Signal Classification with Adversarial Machine Learningcited by 15
- 2018Adversarial Attacks, Regression, and Numerical Stability Regularizationcited by 14
- 2018Deep Learning Power Allocation in Massive MIMOcited by 13
- 2020Over-the-Air Membership Inference Attacks as Privacy Threats for Deep Learning-based Wireless Signal Classifierscited by 13
- 2021Adversarial Attacks on Deep Learning Based Power Allocation in a Massive MIMO Networkcited by 11
- 2019Is AmI (Attacks Meet Interpretability) Robust to Adversarial Examples?cited by 7
- 2021Adversarial Attacks against Deep Learning Based Power Control in Wireless Communicationscited by 4
- 2021Sensing and Classification Using Massive MIMO: A Tensor Decomposition-Based Approachcited by 2
Built on by
Citing papers per year: 2023: 1.
1 paper.