Deep Learning for DDOS Threat Identification in 4.0 Agriculture Technologies
Year: 2026
Type: conference-paper
Abstract: Since increasingly mechanical gear are connected to the web, aggressors are centering on Web of Things systems. Solid deep-learning models that can ensure the systems of Farming 4.0 have been utilized as of late to construct the NIDS. By utilizing LST, CNN, and the coordinates design of LST and CNN for DDoS attacks, an effective and adaptable IDS may be put into put. Valid made the CIC-DDoS2019 dataset, which incorporates a proposition for distinguishing different DDoS attack sorts. The current strategy for creating cleverly interruption location frameworks in DDoS assault discovery on computer organize activity is machine learning, in common, and profound learning, in specific. It was fulfilled utilizing the CICFlowMeter-V3 organize. The standard organize activity dataset, which contains all activity parcels with NetBIOS, Portmap, Syn, UDPLag, UDP, and commonplace generous parcels, was utilized to assess the improvement of profound learning calculations. The show was assessed on exactness, F1-score, exactness, and review in expansion to other measurements. A tall level of precision may be achieved with the assistance of the recommended innovation. With respect to each evaluation parameter, the CNN-LSTM has gotten a score of $100\%$. In arrange to survey the execution of our profound learning show against the current frameworks, we make one in this ponder. As a result, we are able say that this recommended approach offers the most excellent levels of economical assurance against any Farming 4.0 cyber danger. It is economical to hone advanced agribusiness.
Authors: Sanjay Kumar, Sapna Bawankar
Institution: Kalinga University
Language: English
Subfield: Computer Networks and Communications
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7203662099