Skripsi
IMPLEMENTASI METODE LSTM-CNN DALAM SISTEM MULTI-CLASSIFICATION DETEKSI SERANGAN SIBER
Cyberattacks are attempts by individuals or groups to attack computer systems, networks, or other electronic devices with the intent of stealing sensitive data, damaging infrastructure, or creating disruptions in service. There are various types of cyber-attacks, including malware attacks, phishing attacks, DDoS (Distributed Denial of Service) attacks, ransomware attacks, and more. To protect the network security system against various types of cyber-attacks, an attack detection system such as an Intrusion Detection System is needed. IDS is a detector that can investigate activities that occur on internet systems and networks. The method used in this research is Long Short-Term Memory – Convolutional Neural Network (LSTM-CNN). This research uses four different datasets, namely KDD-Cup99, NSL-KDD, ISCX 2012, and CIC-IDS 2018 with various types of attacks in them. By validating training and testing data from 20% to 80%. The output of this research produces the best performance values in the form of Accuracy for the KDD-Cup99 dataset of 99.96%, Recall 99.96%, Specificity 99.99%, Precision 99.96%, F1-Score 99.96%. Accuracy for the NSL-KDD dataset is 99.78%, Recall 99.78%, Specificity 99.94%, Precision 99.78%, F1-Score 99.77%. Accuracy for the ISCX 2012 dataset is 99.58%, Recall 99.58%, Specificity 99.92%, Precision 99.58%, F1-Score 99.58%. Accuracy for the 2018 CIC-IDS dataset is 99.95%, Recall 99.95%, Specificity 100.00%, Precision 99.95%, F1-Score 99.95%.
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2407002678 | T143872 | T1438722024 | Central Library (References) | Available but not for loan - Not for Loan |
No other version available