Machine and Deep Learning for IoT Security and Privacy: Applications, Challenges, and Future Directions

Bharati, Subrato; Podder, Prajoy

doi:10.1155/2022/8951961

Cited by 26 publications

(21 citation statements)

References 307 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• Man-in-the-Middle. One of the earliest kinds of cyber threats was the man-in-the-middle (MiTM) assault (5). Impersonation and spoofing are examples of MiTM attacks.…”

Section: Security Threatsmentioning

confidence: 99%

See 1 more Smart Citation

Implementation of Machine Learning and Deep Learning for Securing the Devices in IOT Systems

Jagannath¹,

Mohite²,

Gupta³

et al. 2023

IJST

View full text Add to dashboard Cite

Objectives: To fix the security issues of devices in internet of things (IOT) systems that arise when Machine learning (ML) and Deep Learning algorithm (DLA) are implemented in the IOT systems. Methods: Each packet of IoT threats has been filtered by using suitable attack model for primary attack detection. In deep learning, network traffic field's information is extracted from of packet and is used as the training features. Attack is proposed to be detected by the use of database-based features of attack. If attack is found then packet will be discarded along with update feedback to filtering stage for primary attack detection. Knowledge Discovery and Data Mining (KDD) dataset is used in this study. Different types of Mirai attack are considered for classification. The performance of the proposed method has been compared in terms of accuracy and execution time with earlier work using traditional ML-DL methods. Findings: The proposed technique is seen to achieve high accuracy level at the least computational time, concurrently with much higher recall and G-mean values Several algorithms are used to secure the IOT devices from various types of threats and a comparison is depicted with their accuracy and execution time. Results show that the proposed methodology using Convolution neural network (CNN) for classification, can achieve the accuracy ~0.9976 with execution time1.30 sec and G-mean 0.7865 only. Novelty: The proposed method is essentially a judiciously configured ML-DL technique which is novel and exhibits better performance in terms of mitigating IoT threats.

show abstract

“…• Man-in-the-Middle. One of the earliest kinds of cyber threats was the man-in-the-middle (MiTM) assault (5). Impersonation and spoofing are examples of MiTM attacks.…”

Section: Security Threatsmentioning

confidence: 99%

“…Owing to the fact that IoT development deals with huge information, a privacy hole is created due to data being improperly checked and insecurely sent. Such inherent weakness is prone to invoke the unique botnet "Mirai" a subject to widespread distributed denial of service (DDoS) attacks (4,5) . The four DL and ML privacy technologies viz.…”

Section: Introductionmentioning

confidence: 99%

Implementation of Machine Learning and Deep Learning for Securing the Devices in IOT Systems

Jagannath¹,

Mohite²,

Gupta³

et al. 2023

IJST

View full text Add to dashboard Cite

show abstract

“…Another type of adversarial attack is known as a poisoning attack [83], where the attacker attempts to manipulate the training data used to develop the machine learning model. This can involve introducing malicious data into the training set or modifying existing data to bias the model towards certain outcomes [12].…”

Section: Adversarial Attacksmentioning

confidence: 99%

Opportunities and Challenges in Applying Machine Learning for Access Control

Nakamura¹,

Tanaka²

2023

Preprint

View full text Add to dashboard Cite

Access control systems are important in regulating who can access physical facilities , computer systems, and data resources. However, traditional access control systems have limitations in adapting to changing user behavior and evolving security threats. We argue that applying machine learning is a promising direction to access control systems can enhance their accuracy, efficiency, and effectiveness. Machine learning can help identify and mitigate security risks in real-time by detecting patterns of suspicious activity that may indicate a security breach or attempted attack. It can also learn to identify anomalies and raise alerts, enabling security personnel to respond quickly and prevent potential security incidents.

show abstract

“…Then central server distributes the aggregated model to each device for the next round of local SGD, and the whole procedure stops until certain termination conditions are met. Although FedSGD solved the challenges of data transmission and privacy leakage of sensitive data (Bharati and Podder, 2022 ; Bharati et al, 2022 ), frequent model uploading and distribution have greatly constrained the performance of federated learning, including slow convergence and low accuracy, and results in the problem of efficiency.…”

Section: Related Workmentioning

confidence: 99%

DWFed: A statistical- heterogeneity-based dynamic weighted model aggregation algorithm for federated learning

Chen

Wang

et al. 2022

Front. Neurorobot.

View full text Add to dashboard Cite

Federated Learning is a distributed machine learning framework that aims to train a global shared model while keeping their data locally, and previous researches have empirically proven the ideal performance of federated learning methods. However, recent researches found the challenge of statistical heterogeneity caused by the non-independent and identically distributed (non-IID), which leads to a significant decline in the performance of federated learning because of the model divergence caused by non-IID data. This statistical heterogeneity is dramatically restricts the application of federated learning and has become one of the critical challenges in federated learning. In this paper, a dynamic weighted model aggregation algorithm based on statistical heterogeneity for federated learning called DWFed is proposed, in which the index of statistical heterogeneity is firstly quantitatively defined through derivation. Then the index is used to calculate the weights of each local model for aggregating federated model, which is to constrain the model divergence caused by non-IID data. Multiple experiments on public benchmark data set reveal the improvements in performance and robustness of the federated models in heterogeneous settings.

show abstract

Machine and Deep Learning for IoT Security and Privacy: Applications, Challenges, and Future Directions

Cited by 26 publications

References 307 publications

Implementation of Machine Learning and Deep Learning for Securing the Devices in IOT Systems

Implementation of Machine Learning and Deep Learning for Securing the Devices in IOT Systems

Opportunities and Challenges in Applying Machine Learning for Access Control

DWFed: A statistical- heterogeneity-based dynamic weighted model aggregation algorithm for federated learning

Contact Info

Product

Resources

About