Procedia Computer Science, Journal Year: 2025, Volume and Issue: 258, P. 3630 - 3639
Published: Jan. 1, 2025
Language: Английский
Procedia Computer Science, Journal Year: 2025, Volume and Issue: 258, P. 3630 - 3639
Published: Jan. 1, 2025
Language: Английский
Informatics, Journal Year: 2024, Volume and Issue: 11(2), P. 32 - 32
Published: May 17, 2024
The Internet of Things (IoT) presents great potential in various fields such as home automation, healthcare, and industry, among others, but its infrastructure, the use open source code, lack software updates make it vulnerable to cyberattacks that can compromise access data services, thus making an attractive target for hackers. complexity has increased, posing a greater threat public private organizations. This study evaluated performance deep learning models classifying cybersecurity attacks IoT networks, using CICIoT2023 dataset. Three architectures based on DNN, LSTM, CNN were compared, highlighting their differences layers activation functions. results show architecture outperformed others accuracy computational efficiency, with rate 99.10% multiclass classification 99.40% binary classification. importance standardization proper hyperparameter selection is emphasized. These demonstrate CNN-based model emerges promising option detecting cyber threats environments, supporting relevance network security.
Language: Английский
Citations
8Security and Privacy, Journal Year: 2024, Volume and Issue: unknown
Published: Oct. 1, 2024
ABSTRACT The Internet of Things (IoT) represents a vast network devices connected to the Internet, making it easier for users connect modern technology. However, complexity these networks and large volume data pose significant challenges in protecting them from persistent cyberattacks, such as distributed denial‐of‐service (DDoS) attacks spoofing. It has become necessary use intrusion detection systems protect networks. Existing IoT face many problems limitations, including high false alarm rates delayed detection. Also, datasets used training may be outdated or sparse, which reduces model's accuracy, mechanisms not defend when any is detected. To address new hybrid deep learning machine methodology proposed that contributes detecting DDoS spoofing attacks, reducing alarms, then implementing defensive measures. In consists three stages: first stage propose method feature selection consisting techniques (correlation coefficient sequential selector); second model by integrating neural with classifier (cascaded long short‐term memory [LSTM] Naive Bayes classifier); third stage, improving defense blocking ports after threats maintaining integrity. evaluating performance methodology, (CIC‐DDoS2019, CIC‐IoT2023, CIC‐IoV2024) were used, also balanced obtain effective results. accuracy 99.91%, 99.88%, 99.77% was obtained. cross‐validation technique test ensure no overfitting. proven its provides powerful solution enhance security can applied fields other attacks.
Language: Английский
Citations
3Computers & Electrical Engineering, Journal Year: 2025, Volume and Issue: 123, P. 110305 - 110305
Published: April 1, 2025
Language: Английский
Citations
0Procedia Computer Science, Journal Year: 2025, Volume and Issue: 258, P. 3630 - 3639
Published: Jan. 1, 2025
Language: Английский
Citations
0