Search

Wireless Multimedia Sensor Network (WMSN) is a network of interconnected sensor nodes equipped with multimedia devices capable to retrieve multimedia as well as scalar sensor data in smart city scenarios. With the progress of smart city development, WMSNs are becoming points of interest. The existing research works on the security of WMSNs show some significant centralized solutions; they are prone to denial of service attacks, central failure, and privacy breaches. Also, these solution are having limitations because of their centralized nature.Therefore, the the proposed scheme adopted the concept of decentralization to achieve more effective and ubiquitous results. As per our best knowledge, we introduce the first decentralized privacy-preserving authentication framework for WMSNs to address the energy and storage challenges. We call our solution PRIvacy-preserving Blockchain-based Authentication for multimeDIa networks (PRIBADI). PRIBADI uses a blockchain framework for authenticated communication between sensor nodes and base stations (as a trusted authority) by using certification and access authentication schemes. We elect trustworthy cluster heads based on weight metrics and these cluster heads forward the information to the Trusted Authority (TA). Subsequently, TA forward large data to the cloud for storage, and the information relevant to certificates and hashes are recorded on the distributed blockchain. Moreover, TA revokes the certificates of malicious sensor nodes and eliminates them from the blockchain. We run a set of experiments on PRIBADI and compare the results with the state-of-the-art models. We use the evaluation criteria of detection accuracy, operation, and energy consumption. We find that PRIBADI is 31.7% better than the existing models. [ABSTRACT FROM AUTHOR]

Industrial applications and automation controls are closely connected with heterogeneous Wireless Sensor Network (WSN); thus, Industrial Internet-of Thing (IIoT) enhances the productivity, scalability, and flexibility of the operations. However, in many cases such as tracking a device or service localization becomes very crucial to state back the operations at times. Existing literature show a various localization solutions, but they face the drawbacks of high energy consumption, and non-coherence in heterogeneity. Besides, in a WSN-based IIoT, non-cooperativeness exists among nodes due to various system and environmental parameters, which make the system resource-exhaustive. In this paper, we introduce a novel localization algorithm that addresses the above-mentioned problems. We call our proposed algorithm RAnge-free Power efficient COoperative Localization (RAPCOL). Specifically, the use of co-operative beacon nodes to broadcast the information to Base Station and low energy consumption highlights the novelty of the work. RAPCOL uses weight metrics for selecting optimal cooperative beacon nodes to prolong the network lifetime. We also introduce an Improvised Particle Swarm Optimization (IPSO) that credits in the contribution in RAPCOL. We run a overall nine sets of experiments to analyze the localization accuracy, effect of beacon nodes, sensor nodes, network connectivity, and sensing field, error frequency, residual energy, time, and network lifetime. A comparative study with the existing localization models shows that RAPCOL is 30 % better than the existing models in terms of accuracy and resource consumption. We observe stable performance of RAPCOL with a differentiated effect of beacon nodes and sensor nodes. We also observe that our proposed IPSO 20 % better in fast convergence to the optimal solution. Though RAPCOL localization time is 12 % higher than other existing protocols, RAPCOL's accuracy and energy saving mechanism make it efficient for IIoTs. [ABSTRACT FROM AUTHOR]

The widespread adoption of smartphones dramatically increases the risk of attacks and the spread of mobile malware, especially on the Android platform. Machine learning-based solutions have been already used as a tool to supersede signature-based anti-malware systems. However, malware authors leverage features from malicious and legitimate samples to estimate statistical difference in-order to create adversarial examples. Hence, to evaluate the vulnerability of machine learning algorithms in malware detection, we propose five different attack scenarios to perturb malicious applications (apps). By doing this, the classification algorithm inappropriately fits the discriminant function on the set of data points, eventually yielding a higher misclassification rate. Further, to distinguish the adversarial examples from benign samples, we propose two defense mechanisms to counter attacks. To validate our attacks and solutions, we test our model on three different benchmark datasets. We also test our methods using various classifier algorithms and compare them with the state-of-the-art data poisoning method using the Jacobian matrix. Promising results show that generated adversarial samples can evade detection with a very high probability. Additionally, evasive variants generated by our attack models when used to harden the developed anti-malware system improves the detection rate up to 50% when using the generative adversarial network (GAN) method. [ABSTRACT FROM AUTHOR]

Malware remains a persistent threat to industrial operations, causing disruptions and financial losses. Traditional malware detection approaches struggle with the increasing complexity of false positives and negatives. However, existing Intrusion Detection Systems (IDSs) often lack the capability to assess the severity of detected malware, crucial for effective threat mitigation. This paper presents a novel model, MAlware DEtection and Severity Analysis for eNcrypted Traffic (MADESANT), designed to detect and analyze malware severity in encrypted traffic data. MADESANT combines Deep Learning (DL)-based intrusion detection with Machine Learning (ML)-based severity analysis, specifically customized for the minutiae of IoT systems and assets. Notably, MADESANT introduces a cascading model integrating a Cascading Forward Back Propagation Neural Network (CFBPNN) with the J48 tree to systematically assess risk factors in network traffic. Our assessment, conducted on diverse encrypted datasets including UNSW-NB15, IoT23, and XIIoTID, highlights the remarkable efficacy of MADESANT. Impressively, it achieves a flawless 0% false positive rate in detecting binary attack instances, surpassing benchmarks set by conventional models. Additionally, MADESANT excels in accurately estimate malware severity, providing invaluable insights into the factors contributing to the risk. To further validate its efficiency, we compared MADESANT against prevalent Neural Network models like FeedForward and Recurrent Neural Networks, with MADESANT emerging as the superior choice. The experimentation encompasses both the entire dataset and subsets generated through meticulous risk factor analysis. These results underscore MADESANT’s prowess in not only identifying malware but also in evaluating its potential impact, signifying a significant leap forward in industrial cybersecurity. [ABSTRACT FROM AUTHOR]

The evolving behavior of the attacks may affect the decision boundaries of the trained machine learning models. The issue has not been well investigated, especially with hypervisor-based security solutions where virtual machine (VM)’s network artifacts are introspected and analyzed. In this paper, we proposed a sustainable and explainable flow-filtering-based concept drift-driven network intrusion detection approach, called ‘SFC-NIDS’ which introspects network activities by analyzing VM traffic profile. The VM traffic is captured and pre-processed at the hypervisor to extract important network artifacts. The redundant and trivial network flows have been filtered using the proposed gradient descent-based flow filtering mechanism and validated using explainability. SFC-NIDS employs auto-encoders to reconstruct the traffic features to capture additional patterns. Afterward, the 1D-convolution neural network has been employed to learn and detect malicious attack flows. The model’s sustainability is ensured by integrating the drift detection mechanism with the decision model to retrain it with evolving attack patterns. The approach has been validated with virtual network traffic artifacts collected at the hypervisor and provides 98.9% accuracy, 99.03%, and F1-Score. In addition, the approach has also been validated using the KDD99 dataset, showcasing an accuracy of 99.97% and an F1-Score of 99.98%. [ABSTRACT FROM AUTHOR]