IEEE Internet of Things Journal · 2024 · 59 citations · 97 references
ComputingComputer ScienceCybersecurityInternet Of ThingsMachine LearningNetwork SecurityCellular Network SecurityEdge SecurityPhysical Layer SecurityWireless Device SecurityAdversarial RobustnessAttack MitigationCell-free Massive MimoDeep Learning For IotInternet Of Things Vulnerability AnalysisIot Network SecurityMachine-learning AttacksMassive Multiple-input Multiple-output Multiple Access
The Internet of Things (IoT) and massive IoT systems are key to sixth-generation (6G) networks due to dense connectivity, ultra-reliability, low latency, and high throughput. Artificial intelligence, including deep learning and machine learning, offers solutions for optimizing and deploying cutting-edge technologies for future radio communications. However, these techniques are vulnerable to adversarial attacks, leading to degraded performance and erroneous predictions, outcomes unacceptable for ubiquitous networks. This survey extensively addresses adversarial attacks and defense methods in 6G network-assisted IoT systems. The theoretical background and up-to-date research on adversarial attacks and defenses are discussed. Furthermore, we provide Monte Carlo simulations to validate the effectiveness of adversarial attacks compared to jamming attacks. Additionally, we examine the vulnerability of 6G IoT systems by demonstrating attack strategies applicable to key technologies, including reconfigurable intelligent surfaces, massive multiple-input multiple-output (MIMO)/cell-free massive MIMO, satellites, the metaverse, and semantic communications. Finally, we outline the challenges and future developments associated with adversarial attacks and defenses in 6G IoT systems.
97
Practical Black-Box Attacks against Machine Learning
Nicolas Papernot, Patrick McDaniel, Ian Goodfellow et al. · 2017 · 3.5K citations
Boosting Adversarial Attacks with Momentum
Yinpeng Dong, Fangzhou Liao, Tianyu Pang et al. · 2018 · 2.9K citations