Adversarial Machine Learning Security Problems for 6G: mmWave Beam Prediction Use-Case

Catak, Evren; Çatak, Ferhat Özgür; Moldsvor, Arild

doi:10.1109/blackseacom52164.2021.9527756

Cited by 22 publications

(18 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, sophisticated AI-based algorithms can help to model the highly nonlinear correlations and estimate the channel characteristics [20]. In our recent papers [21] and [22], adversarial attacks and mitigation methods have been investigated along with the proposed framework for mmWave beamforming prediction models in next-generation networks. This study provides a comprehensive vulnerability analysis of deep learning (DL)based channel estimation models trained with the dataset obtained from MATLAB's 5G toolbox for adversarial attacks and defensive distillation-based mitigation methods.…”

Section: Purpose and Contributionsmentioning

confidence: 99%

Defensive Distillation-Based Adversarial Attack Mitigation Method for Channel Estimation Using Deep Learning Models in Next-Generation Wireless Networks

Çatak

Kuzlu

Catak³

et al. 2022

IEEE Access

Self Cite

View full text Add to dashboard Cite

Future wireless networks (5G and beyond), also known as Next Generation or NextG, are the vision of forthcoming cellular systems, connecting billions of devices and people together. In the last decades, cellular networks have dramatically grown with advanced telecommunication technologies for high-speed data transmission, high cell capacity, and low latency. The main goal of those technologies is to support a wide range of new applications, such as virtual reality, metaverse, telehealth, online education, autonomous and flying vehicles, smart cities, smart grids, advanced manufacturing, and many more. The key motivation of NextG networks is to meet the high demand for those applications by improving and optimizing network functions. Artificial Intelligence (AI) has a high potential to achieve these requirements by being integrated into applications throughout all network layers. However, the security concerns on network functions of NextG using AI-based models, i.e., model poising, have not been investigated deeply. It is crucial to protect the next-generation cellular networks against cybersecurity threats, especially adversarial attacks. Therefore, it needs to design efficient mitigation techniques and secure solutions for NextG networks using AI-based methods. This paper proposes a comprehensive vulnerability analysis of deep learning (DL)-based channel estimation models trained with the dataset obtained from MATLAB's 5G toolbox for adversarial attacks and defensive distillation-based mitigation methods. The adversarial attacks produce faulty results by manipulating trained DL-based models for channel estimation in NextG networks while making models more robust against attacks through mitigation methods. This paper also presents the performance of the proposed defensive distillation mitigation method for each adversarial attack. The results indicate that the proposed mitigation method can defend the DL-based channel estimation models against adversarial attacks in NextG networks.

show abstract

Section: Purpose and Contributionsmentioning

confidence: 99%

Defensive Distillation-Based Adversarial Attack Mitigation Method for Channel Estimation Using Deep Learning Models in Next-Generation Wireless Networks

Çatak

Kuzlu

Catak³

et al. 2022

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…In our recent works [11] and [9], we only investigated FGSM attacks, which can be mitigated using the adversarial training method. In this work, four different adversarial machine learning methods (FGSM, BIM, PGD, and MIM) are investigated to build robust beamforming DL models using two mitigation methods.…”

Section: Purpose and Contributionsmentioning

confidence: 99%

The Adversarial Security Mitigations of mmWave Beamforming Prediction Models using Defensive Distillation and Adversarial Retraining

Kuzlu¹,

Çatak²,

Cali³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

The design of a security scheme for beamforming prediction is critical for next-generation wireless networks (5G, 6G, and beyond). However, there is no consensus about protecting the beamforming prediction using deep learning algorithms in these networks. This paper presents the security vulnerabilities in deep learning for beamforming prediction using deep neural networks (DNNs) in 6G wireless networks, which treats the beamforming prediction as a multi-output regression problem. It is indicated that the initial DNN model is vulnerable against adversarial attacks, such as Fast Gradient Sign Method (FGSM), Basic Iterative Method (BIM), Projected Gradient Descent (PGD), and Momentum Iterative Method (MIM), because the initial DNN model is sensitive to the perturbations of the adversarial samples of the training data. This study also offers two mitigation methods, such as adversarial training and defensive distillation, for adversarial attacks against artificial intelligence (AI)-based models used in the millimeter-wave (mmWave) beamforming prediction. Furthermore, the proposed scheme can be used in situations where the data are corrupted due to the adversarial examples in the training data. Experimental results show that the proposed methods effectively defend

show abstract

“…Therefore, sophisticated AI-based algorithms can help to model the highly nonlinear correlations and estimate the channel characteristics [19]. In our recent papers [20] and [21], adversarial attacks and mitigation methods have been investigated along with the proposed framework for mmWave beamforming prediction models in next-generation networks. This paper implements widely used adversarial attacks from Fast Gradient Sign Method (FGSM), Basic Iterative Method (BIM), Projected Gradient Descent (PGD), Momentum Iterative Method (MIM), to Carlini & Wagner (C&W) as well as a defensive distillation based mitigation method for DL-based channel estimation models in next-generation wireless networks.…”

Section: Purpose and Contributionsmentioning

confidence: 99%

Defensive Distillation based Adversarial Attacks Mitigation Method for Channel Estimation using Deep Learning Models in Next-Generation Wireless Networks

Çatak¹,

kuzlu²,

catak³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

<p>Future wireless networks \textcolor{black}{(5G and beyond),} also known as Next Generation or NextG, are the vision of forthcoming cellular systems, connecting billions of devices and people together. In the last decades, cellular networks have been dramatically growth with advanced telecommunication technologies for high-speed data transmission, high cell capacity, and low latency. The main goal of those technologies is to support a wide range of new applications, such as virtual reality, metaverse, telehealth, online education, autonomous and flying vehicles, smart cities, smart grids, advanced manufacturing, and many more. The key motivation of NextG networks is to meet the high demand for those applications by improving and optimizing network functions. Artificial Intelligence (AI) has a high potential to achieve these requirements by being integrated in applications throughout all layers of the network. However, the security concerns on network functions of NextG using AI-based models, i.e., model poising, have not been investigated deeply. It is crucial to protect the next-generation cellular networks against cyber attacks, especially adversarial attacks. Therefore, it needs to design efficient mitigation techniques and secure solutions for NextG networks using AI-based methods. This paper proposes a comprehensive vulnerability analysis of deep learning (DL)-based channel estimation models trained with the dataset obtained from MATLAB's 5G toolbox for adversarial attacks and defensive distillation-based mitigation methods. The adversarial attacks produce faulty results by manipulating trained DL-based models for channel estimation in NextG networks, while making models more robust against any attacks through mitigation methods. This paper also presents the performance of the proposed defensive distillation mitigation method for each adversarial attack against the channel estimation model. The results indicated that the proposed mitigation method can defend the DL-based channel estimation models against adversarial attacks in NextG networks.</p>

show abstract

Adversarial Machine Learning Security Problems for 6G: mmWave Beam Prediction Use-Case

Cited by 22 publications

References 10 publications

Defensive Distillation-Based Adversarial Attack Mitigation Method for Channel Estimation Using Deep Learning Models in Next-Generation Wireless Networks

Defensive Distillation-Based Adversarial Attack Mitigation Method for Channel Estimation Using Deep Learning Models in Next-Generation Wireless Networks

The Adversarial Security Mitigations of mmWave Beamforming Prediction Models using Defensive Distillation and Adversarial Retraining

Defensive Distillation based Adversarial Attacks Mitigation Method for Channel Estimation using Deep Learning Models in Next-Generation Wireless Networks

Contact Info

Product

Resources

About