Figure 1:
Overview of the AI ecosystem highlighting the roles and interconnections between ML, DL, and LLM. AI, artificial intelligence; CNNs, convolutional neural network; DL, deep learning; LLM, large language models; ML, machine learning.
Figure 2:
Network diagram depicting components involved in DDoS defense, including internet access points, firewalls, switches, IDS, and end-user devices. DDoS, distributed denial of service; IDS, intrusion detection systems.
Figure 3:
Architectural overview of an IDS, detailing its core components, detection methodologies, data integration points, and response mechanisms. IDS, intrusion detection systems.
Figure 4:
CNN. CNN, convolutional neural network.
Table 1:
CCICDDoS2019 dataset
| Type | Records |
|---|---|
| Benign | 56,863 |
| LDAP | 2,179,930 |
| TFTP | 20,082,580 |
| DNS | 5,071,011 |
| NetBIOS | 4,093,279 |
| MSSQL | 4,522,492 |
| SSDP | 2,610,611 |
| NTP | 1,202,642 |
| SNMP | 5,159,870 |
| UDP | 3,134,645 |
| SYN | 1,582,289 |
| UDP-Lag | 366,461 |
| WebDDoS | 439 |
| Total | 50,063,112 |
[i] LDAP, lightweight directory access protocol; MSSQL, microsoft SQL server; NTP, network time protocol; SNMP, simple network management protocol; SSDP, simple service discovery protocol; SYN, synchronize; TFTP, trivial file transfer protocol; UDP-Lag, UDP-based lag attack; WebDDoS, web-based distributed denial of service.
Figure 5:
Proposed architecture processing network traffic data through CNN for DDoS attack detection, incorporating PCA and SMOTE for data preparation. CNN, convolutional neural network; DDoS, distributed denial of service; PCA, principal component analysis; SMOTE, Synthetic Minority Oversampling Technique.
Figure 6:
Proposed architecture diagram illustrating the dual-path approach for DDoS attack detection, featuring both CNN and ViT layers. CNN, convolutional neural network; DDoS, distributed denial of service; ViT, vision transformers.
Figure 7:
Performance and efficiency of CNN models: This graph shows key performance metrics—Test Accuracy, Training Accuracy, Precision, Recall, and F1 Score—across three CNN configurations (CNN-30, CNN-20, CNN-10). It also illustrates the reduction in training time for each model, emphasizing the balance between model accuracy and computational efficiency. CNN, convolutional neural networks.
Figure 8:
Confusion matrix. DDoS, distributed denial of service.