The pursuit to spot abnormal behaviors in and out of a network system is what led to a system known as intrusion detection systems for soft computing besides many researchers have applied machine learning around this area. Obviously, a single classifier alone in the classifications seems impossible to control network intruders. This limitation is what led us to perform dimensionality reduction by means of correlation-based feature selection approach (CFS approach) in addition to a refined ensemble model. The paper aims to improve the Intrusion Detection System (IDS) by proposing a CFS + Ensemble Classifiers (Bagging and Adaboost) which has high accuracy, high packet detection rate, and low false alarm rate. Machine Learning Ensemble Models with base classifiers (J48, Random Forest, and Reptree) were built. Binary classification, as well as Multiclass classification for KDD99 and NSLKDD datasets, was done while all the attacks were named as an anomaly and normal traffic. Class labels consisted of five major attacks, namely Denial of Service (DoS), Probe, User-to-Root (U2R), Root to Local attacks (R2L), and Normal class attacks. Results from the experiment showed that our proposed model produces 0 false alarm rate (FAR) and 99.90% detection rate (DR) for the KDD99 dataset, and 0.5% FAR and 98.60% DR for NSLKDD dataset when working with 6 and 13 selected features.

The recent developments in fog computing architecture and cloud of things (CoT) technology includes data mining management and artificial intelligence operations. However, one of the major challenges of this model is vulnerability to security threats and cyber-attacks against the fog computing layers. In such a scenario, each of the layers are susceptible to different intimidations, including the sensed data (edge layer), computing and processing of data (fog (layer), and storage and management for public users (cloud). The conventional data storage and security mechanisms that are currently in use appear to not be suitable for such a huge amount of generated data in the fog computing architecture. Thus, the major focus of this research is to provide security countermeasures against medical data mining threats, which are generated from the sensing layer (a human wearable device) and storage of data in the cloud database of internet of things (IoT). Therefore, we propose a public-permissioned blockchain security mechanism using elliptic curve crypto (ECC) digital signature that that supports a distributed ledger database (server) to provide an immutable security solution, transaction transparency and prevent the patient records tampering at the IoTs fog layer. The blockchain technology approach also helps to mitigate these issues of latency, centralization, and scalability in the fog model.

Sybil security threat in vehicular ad hoc networks (VANETs) has attracted much attention in recent times. The attacker introduces malicious nodes with multiple identities. As the roadside unit fails to synchronize its clock with legitimate vehicles, unintended vehicles are identified, and therefore erroneous messages will be sent to them. This paper proposes a novel biologically inspired spider-monkey time synchronization technique for large-scale VANETs to boost packet delivery time synchronization at minimized energy consumption. The proposed technique is based on the metaheuristic stimulated framework approach by the natural spider-monkey behavior. An artificial spider-monkey technique is used to examine the Sybil attacking strategies on VANETs to predict the number of vehicular collisions in a densely deployed challenge zone. Furthermore, this paper proposes the pseudocode algorithm randomly distributed for energy-efficient time synchronization in two-way packet delivery scenarios to evaluate the clock offset and the propagation delay in transmitting the packet beacon message to destination vehicles correctly. The performances of the proposed technique are compared with existing protocols. It performs better over long transmission distances for the detection of Sybil in dynamic VANETs' system in terms of measurement precision, intrusion detection rate, and energy efficiency.

The concept of Federated Learning (FL) is a distributed-based machine learning (ML) approach that trains its model using edge devices. Its focus is on maintaining privacy by transmitting gradient updates along with users' learning parameters to the global server in the process of training as well as preserving the integrity of data on the user-end of internet of medical things (IoMT) devices. Instead of a direct use of user data, the training which is performed on the global server is done on the parameters while the model modification is performed locally on IoMT devices. But the major drawback of this federated learning approach is its inability to preserve user privacy complete thereby resulting in gradients leakage. Thus, this study first presents a summary of the process of learning and further proposes a new approach for federated medical recommender system which employs the use of homomorphic cryptography to ensure a more privacy-preservation of user gradients during recommendations. The experimental results indicate an insignificant decrease with respect to the metrics of accuracy, however, a greater percentage of user-privacy is achieved. Further analysis also shows that performing computations on encrypted gradients at the global server scarcely has any impact on the output of the recommendation while guaranteeing a supplementary secure channel for transmitting user-based gradients back and forth the global server. The result of this analysis indicates that the performance of federated stochastic modification minimized gradient (FSMMG) algorithm is greatly increased at every given increase in the number of users and a good convergence is achieved as well. Also, experiments indicate that when compared against other existing techniques, the proposed FSMMG outperforms at 98.3% encryption accuracy.