Walid I. Khedr

In this paper, we propose a new hybrid model, called AVE, that integrates the strengths of Autoencoder (AE) and Variational Autoencoder (VAE) to enhance outlier detection for numerous high-dimensional datasets. The proposed architecture leverages the reconstruction strengths of AE and the regularized latent space of VAE to build a stable framework for anomaly detection. Our experimental evaluation is conducted on 16 standard test sets from various domains. The results show that the AVE architecture outperforms the standalone architecture of AE, VAE, and other compared algorithms. The AVE architecture, specifically, achieves an average precision of 0.6925 and an average ROC-AUC of 0.8902 across the subsets of this test set. It surpasses the second-best architecture by 25.99% for precision and 5.47% for ROC-AUC. It surpasses AE and VAE architectures by 67.26% and 45.44% in precision, and by 7.71% and 10.03% in ROC-AUC, respectively. It achieves the best accuracy on 12 of the 16 datasets and the optimal ROC-AUC on 5 of them. Our findings demonstrate that AVE is a more reliable and precise method for detecting outliers, particularly in complex, high-dimensional datasets, making it an effective solution for real-world applications.

Federated learning (FL) is a machine learning technique where clients exchange only local model updates with a central server that combines them to create a global model after local training. While FL offers privacy benefits through local training, privacy-preserving strategies are needed since model updates can leak training data information due to various attacks. To enhance privacy and attack robustness, techniques like homomorphic encryption (HE), Secure Multi-Party Computation (SMPC), and the Private Aggregation of Teacher Ensembles (PATE) can be combined with FL. Currently, no study has combined more than two privacy-preserving techniques with FL or comparatively analyzed their combinations. We conducted a comparative study of privacy-preserving techniques in FL, analyzing performance and security. We implemented FL using an artificial neural network (ANN) with a Malware Dataset from Kaggle for malware detection. To enhance privacy, we proposed models combining FL with the PATE, SMPC, and HE. All models were evaluated against poisoning attacks (targeted and untargeted), a backdoor attack, a model inversion attack, and a man in the middle attack. The combined models maintained performance while improving attack robustness. FL_SMPC, FL_CKKS, and FL_CKKS_SMPC improved both their performance and attack resistance. All the combined models outperformed the base FL model against the evaluated attacks. FL_PATE_CKKS_SMPC achieved the lowest backdoor attack success rate (0.0920). FL_CKKS_SMPC best resisted untargeted poisoning attacks (0.0010 success rate). FL_CKKS and FL_CKKS_SMPC best defended against targeted poisoning attacks (0.0020 success rate). FL_PATE_SMPC best resisted model inversion attacks (19.267 MSE). FL_PATE_CKKS_SMPC best defended against man in the middle attacks with the lowest degradation in accuracy (1.68%), precision (1.94%), recall (1.68%), and the F1-score (1.64%).

Distributed Denial of Service (DDoS) and Address Resolution Protocol (ARP) attacks pose significant threats to the security of Software-Defined Internet of Things (SD-IoT) networks. The standard Software-Defined Networking (SDN) architecture faces challenges in effectively detecting, preventing, and mitigating these attacks due to its centralized control and limited intelligence. In this paper, we present P4-HLDMC, a novel collaborative secure framework that combines machine learning (ML), stateful P4, and a hierarchical logically distributed multi-controller architecture. P4-HLDMC overcomes the limitations of the standard SDN architecture, ensuring scalability, performance, and an efficient response to attacks. It comprises four modules: the multi-controller dedicated interface (MCDI) for real-time attack detection through a distributed alert channel (DAC), the MSMPF, a P4-enabled stateful multi-state matching pipeline function for analyzing IoT network traffic using nine state tables, the modified ensemble voting (MEV) algorithm with six classifiers for enhanced detection of anomalies in P4-extracted traffic patterns, and an attack mitigation process distributed among multiple controllers to effectively handle larger-scale attacks. We validate our framework using diverse test cases and real-world IoT network traffic datasets, demonstrating high detection rates, low false-alarm rates, low latency, and short detection times compared to existing methods. Our work introduces the first integrated framework combining ML, stateful P4, and SDN-based multi-controller architecture for DDoS and ARP detection in IoT networks.

The absence of standards and the diverse nature of the Internet of Things (IoT) have made security and privacy concerns more acute. Attacks such as distributed denial of service (DDoS) are becoming increasingly widespread in IoT, and the need for ways to stop them is growing. The use of newly formed Software-Defined Networking (SDN) significantly lowers the computational burden on IoT network nodes and makes it possible to perform more security measurements. This paper proposes an SDN-based, four-module DDoS attack detection and mitigation framework for IoT networks called FMDADM. The proposed FMDADM framework comprises four main modules and five-tier architecture. The first module implements an early detection process based on the average drop rate (ADR) principle using a 32-packet window size. The second module uses a novel double-check mapping function (DCMF), that aids in earlier attack detection at the data plane level. The third module is an ML-based detection application comprising four phases: data preprocessing, feature extraction, training and testing, and classification. This module detects DDoS attacks using only seven features: two selected and five newly computed features. The last module introduces an attack mitigation process. We applied the proposed framework to three test cases: one single-node attack test case and two multi-node attack test cases, all with real IoT traffic generated and deployed in Mininet-IoT. The proposed FMDADM framework efficiently detects DDoS attacks at high and low rates, can discriminate between attack traffic and flash crowds, and protects both local and remote IoT nodes by preventing infection from propagating to the ISP level. The FMDADM outperformed most existing cutting-edge approaches across ten different evaluation criteria. According to the experimental results, FMDADM achieved the following accuracy, precision, F-measure, recall, specificity, negative predictive value, false positive rate, false detection rate, false negative rate, and average detection time benchmarks:- 99.79%, 99.43%, 99.77%, 99.79%, 99.95%, 00.21%, 00.91%, 00.23%, and 2.64 μs, respectively.