Darknet Traffic Big-Data Analysis and Network Management for Real-Time Automating of the Malicious Intent Detection Process by a Weight Agnostic Neural Networks Framework

Abstract

Attackers are perpetually modifying their tactics to avoid detection and frequently leverage legitimate credentials with trusted tools already deployed in a network environment, making it difficult for organizations to proactively identify critical security risks. Network traffic analysis products have emerged in response to attackers’ relentless innovation, offering organizations a realistic path forward for combatting creative attackers. Additionally, thanks to the widespread adoption of cloud computing, Device Operators (DevOps) processes, and the Internet of Things (IoT), maintaining effective network visibility has become a highly complex and overwhelming process. What makes network traffic analysis technology particularly meaningful is its ability to combine its core capabilities to deliver malicious intent detection. In this paper, we propose a novel darknet traffic analysis and network management framework to real-time automating the malicious intent detection process, using a weight agnostic neural networks architecture. It is an effective and accurate computational intelligent forensics tool for network traffic analysis, the demystification of malware traffic, and encrypted traffic identification in real time. Based on a weight agnostic neural networks (WANNs) methodology, we propose an automated searching neural net architecture strategy that can perform various tasks such as identifying zero-day attacks. By automating the malicious intent detection process from the darknet, the advanced proposed solution is reducing the skills and effort barrier that prevents many organizations from effectively protecting their most critical assets.

A Novel Deep-Learning-Based Framework for the Classification of Cardiac Arrhythmia

“…Motivated by the conversion of ECG into the 2D signal, we propose a novel deep-learning-based framework for classifying sixteen cardiac arrhythmia classes. A plethora of pre-trained D-CNNs, such as AlexNet [ 20 ], ResNet-50 [ 21 ], VGG-19 [ 22 ], Inception v3 [ 23 ], GoogLeNet [ 24 ], ShuffleNet [ 25 ], SqueezeNet [ 26 ], EfficientNetb0 [ 27 ], Xception [ 28 ], and DarkNet-53 [ 29 ], as well as the novel attention-based CNN ArrhythmiaNet, have been used for the feature extraction of 2D time–frequency representations of ECG beats. These features are reduced, and the classifier is trained using reduced features.…”

Scnta

“…The control also uses a predetermined timeout for Capturing_of_Packets (CoP) and result presentation. The ability to test various methods for sub-Categorization_of_Flow (CoF), as explained in (Chen et al,2021), is the justification for implementing a Reconciliation_of_Flow (RoF) Methods, in spite of existence of multiple tools, libraries and packages to achieve the task, like libNIDS (Garcia et al,2021), TcpTrace (Demertzis et al,2021), and WireShark (Goodall et al,2018). Furthermore, as demonstrated by (Xu and Zhu, 2021) and (Pereira et al, 2015), evaluating approaches for run-time TCP stream reconciliation is now possible, which is critical at implementation of high-momentum traffic categorization framework.…”

“…The caught packets are sent to a reconciliation process in the training phase, which associates every packet with its respective flows. An parallel procedure collects analytical Details by Packet-Headers, uses an attribute selection algorithm to pick the most important attributes, and marks the flows using the well-known port system(Demertzis et al,2021). The traffic flows are used to train a supervised categorization system that is arranged in a spatial presentation…”

An Interactive Self-Learning Game and Evolutionary Approach Based on Non-Cooperative Equilibrium

“…The five neurons in the output layer correspond to the five base actions, and a Softmax normalization function is used to ensure that all actions sum to one, which is defined as shown in Equation (12).…”

“…For instance, Malysheva A. et al [11] proposed a new MAGNet method for multi-agent reinforcement learning. Based on a weight agnostic neural networks (WANNs) methodology, an automated searching neural net architecture strategy was proposed that can perform various tasks such as identifying zero-day attacks [12]. Sheikh, HU et al [13] proposed the DE-MADDPG method, which can achieve better multi-agent learning by coordinating local and global rewards.…”