Edge Security: Challenges and Issues
Not on the map. Why?
Abstract (arXiv)
Edge computing is a paradigm that shifts data processing services to the network edge, where data are generated. While such an architecture provides faster processing and response, among other benefits, it also raises critical security issues and challenges that must be addressed. This paper discusses the security threats and vulnerabilities emerging from the edge network architecture spanning from the hardware layer to the system layer. We further discuss privacy and regulatory compliance challenges in such networks. Finally, we argue the need for a holistic approach to analyze edge network security posture, which must consider knowledge from each layer.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 51 of its 273 references that are in the map. First posted on arXiv 14 Jun 2022.
Builds on
51 of 273 references.
References · 51
- 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
- 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
- 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
- 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,106
- 2016Practical Black-Box Attacks against Machine Learningcited by 903
- 2015The Limitations of Deep Learning in Adversarial Settingscited by 790
- 2018How To Backdoor Federated Learningcited by 765
- 2016Stealing Machine Learning Models via Prediction APIscited by 619
- 2018Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networkscited by 519
- 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
- 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 457
- 2020Backdoor Learning: A Surveycited by 426
38 more
- 2018Adaptive Federated Learning in Resource Constrained Edge Computing Systemscited by 409
- 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 351
- 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 288
- 2020Data Poisoning Attacks Against Federated Learning Systemscited by 275
- 2020MCUNet: Tiny Deep Learning on IoT Devicescited by 273
- 2018Generating Adversarial Examples with Adversarial Networkscited by 258
- 2018Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learningcited by 225
- 2018Machine Learning with Membership Privacy using Adversarial Regularizationcited by 186
- 2019Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inferencecited by 175
- 2020TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systemscited by 165
- 2019Privacy Risks of Securing Machine Learning Models against Adversarial Examplescited by 141
- 2018Towards the Development of Realistic Botnet Dataset in the Internet of Things for Network Forensic Analytics: Bot-IoT Datasetcited by 99
- 2020An Embarrassingly Simple Approach for Trojan Attack in Deep Neural Networkscited by 97
- 2020Byzantine-Resilient Secure Federated Learningcited by 93
- 2021PPFL: Privacy-preserving Federated Learning with Trusted Execution Environmentscited by 93
- 2022Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challengescited by 84
- 2020DarkneTZ: Towards Model Privacy at the Edge using Trusted Execution Environmentscited by 58
- 2021Model Extraction and Adversarial Transferability, Your BERT is Vulnerable!cited by 53
- 2018Spectre Attacks: Exploiting Speculative Executioncited by 47
- 2018A First Look at Deep Learning Apps on Smartphonescited by 47
- 2021Challenges and Approaches for Mitigating Byzantine Attacks in Federated Learningcited by 47
- 2020Mind Your Weight(s): A Large-scale Study on Insufficient Machine Learning Model Protection in Mobile Appscited by 36
- 2018Machine learning for Internet of Things data analysis: A surveycited by 29
- 2021Smart at what cost? Characterising Mobile Deep Neural Networks in the wildcited by 25
- 2019Generative Adversarial Network for Wireless Signal Spoofingcited by 21
- 2017Software Grand Exposure: SGX Cache Attacks Are Practicalcited by 15
- 2020Generative Adversarial Network in the Air: Deep Adversarial Learning for Wireless Signal Spoofingcited by 14
- 2021Context-Dependent Anomaly Detection for Low Altitude Traffic Surveillancecited by 10
- 2020Adversarial Machine Learning based Partial-model Attack in IoTcited by 9
- 2017CacheZoom: How SGX Amplifies The Power of Cache Attackscited by 7
- 2019Internet of Things Security, Device Authentication and Access Control: A Reviewcited by 3
- 2020TeeRex: Discovery and Exploitation of Memory Corruption Vulnerabilities in SGX Enclavescited by 2
- 2021Security Risks of Porting C Programs to WebAssemblycited by 2
- 2017Energy Attacks on Mobile Devicescited by 1
- 2019StackVault: Protection from Untrusted Functionscited by 1
- 2019Uncheatable Machine Learning Inferencecited by 1
- 2019Protecting Actuators in Safety-Critical IoT Systems from Control Spoofing Attackscited by 1
- 2021Person Re-identification Attack on Wearable Sensingcited by 1
50 most cited of 51 All 51 (JSON)
Built on by
Citing papers per year: 2023: 2; 2024: 1.
3 papers.