Kafka‐Shield: Kafka Streams‐based distributed detection scheme for IoT traffic‐based DDoS attacks

Security and Privacy, Journal Year: 2024, Volume and Issue: 7(6)

Published: May 21, 2024

Abstract With the rapid proliferation of insecure Internet Things (IoT) devices, security Internet‐based applications and networks has become a prominent concern. One most significant threats encountered in IoT environments is Distributed Denial Service (DDoS) attack. This attack can severely disrupt critical services prevent smart devices from functioning normally, leading to severe consequences for businesses individuals. It aims overwhelm victims' resources, websites, other by flooding them with massive packets, making inaccessible legitimate users. Researchers have developed multiple detection schemes detect DDoS attacks. As technology advances facilitating factors increased, it challenge identify such powerful attacks real‐time. In this paper, we propose novel distributed scheme network traffic‐based deploying Kafka Streams processing framework named Kafka‐Shield. The Kafka‐Shield comprises two stages: design deployment. Firstly, designed on Hadoop cluster employing highly scalable H2O.ai machine learning platform. Secondly, portable, scalable, deployed framework. To analyze incoming traffic data categorize into nine target classes real time. Additionally, stores each flow input features predicted outcome File System (HDFS). enables development new models or updating current ones. validate effectiveness Kafka‐Shield, performed analysis using various configured scenarios. experimental results affirm Kafka‐Shield's remarkable efficiency detecting rate over 99% process 0.928 million traces nearly 3.027 s.

Language: Английский

---

Distributed Ensemble Method Using Deep Learning to Detect DDoS Attacks in IoT Networks

Arabian Journal for Science and Engineering, Journal Year: 2024, Volume and Issue: unknown

Published: May 29, 2024

Language: Английский

---

The Guardian Node Slow DoS Detection Model for Real-Time Application in IoT Networks

Sensors, Journal Year: 2024, Volume and Issue: 24(17), P. 5581 - 5581

Published: Aug. 28, 2024

The pernicious impact of malicious Slow DoS (Denial Service) attacks on the application layer and web-based Open Systems Interconnection model services like

Language: Английский

---

Harnessing Blockchain with Ensemble Deep Learning based Distributed DoS Attack Detection in IoT-Assisted Secure Consumer Electronics Systems

Fractals, Journal Year: 2024, Volume and Issue: 32(09n10)

Published: Sept. 24, 2024

Consumer electronics (CE) and the Internet of Things (IoTs) are transforming daily routines by integrating smart technology into household gadgets. IoT allows devices to link communicate from with better functions, remote control, automation various complex systems simulation platforms. The quick progress in has continuously driven further connected intelligent CEs, shaping more cities homes. Blockchain (BC) is emerging as a promising offering immutable distributed ledgers that improve security integrity data. However, even BC resilience, ecosystem remains vulnerable Distributed Denial Service (DDoS) attacks. In contrast, malicious actor overwhelms network traffic, disrupting services compromising device functionality. Incorporating infrastructure presents groundbreaking techniques alleviate these threats. networks can detect respond DDoS attacks real time leveraging cryptographic decentralized consensus mechanisms, which safeguard against disruptions enhance resilience. There must be reliable mechanism recognition based on adequate identify whether have happened or not system. Artificial intelligence (A) most common technique uses machine learning (ML) deep (DL) recognize cyber This research new Ensemble Deep Learning-based DoS Attack Detection (BCEDL-DDoSD) approach platform. primary intention BCEDL-DDoSD leverage DL-based attack process utilized enable secure data transmission process. approach, Z-score normalization initially employed measure input Besides, selection features takes place using Fractal Wombat optimization algorithm (WOA). For recognition, BCDL-DDoSD applies an ensemble three models, namely denoising autoencoder (DAE), gated recurrent unit (GRU), long short-term memory (LSTM). Lastly, orca predator (OPA)-based hyperparameter tuning procedure been implemented select parameter value DL models. A sequence simulations made benchmark database authorize performance approach. results showed performs than other techniques.

Language: Английский

---

Cybersecurity Framework Development for BoTNet Attack Detection using ISSOA based Attention Recurrent Autoencoder

Published: Aug. 23, 2024

Language: Английский

---