ECTI Transactions on Computer and Information Technology (ECTI-CIT)

An Effective Prevention Approach against ARP Cache Poisoning Attacks in MikroTik-based Networks

Ekarin Suethanuwong — 2024-11-16

Nowadays, leading manufacturers of enterprise-grade networking devices offer the dynamic ARP inspection (DAI) feature in their Ethernet Switches to detect and prevent ARP cache poisoning attacks from malicious hosts. However, MikroTik Ethernet switches do not yet support this feature. Within MikroTik-based networks, three potential approaches exist to prevent ARP cache poisoning attacks, each with drawbacks. This paper proposes an innovative approach called Gateway-controlled ARP (GCA) to prevent ARP cache poisoning attacks on a router-on-a-stick (RoaS) network using MikroTik networking devices, where a single router performs inter-VLAN routing through one physical interface. With this approach, all Ethernet switches are configured to forward ARP messages from hosts directly to the router for inspection and handling. A RouterOS script based on the GCA approach was implemented and executed on the router to handle all incoming ARP requests from any host in all VLANs, ensuring all hosts receive legitimate ARP responses from the router. This approach can effectively prevent spoofed ARP packets sent by malicious attackers. This approach was tested and evaluated on an actual RoaS network, focusing on processing time, CPU Load, and response time. The evaluation results show that the approach effectively prevents ARP cache poisoning attacks.

A Study on Bilingual Deep Learning PIS Neural Network Model Based on Graph-Text Modal Fusion

Yan Xie — 2024-11-16

This research investigates a multilingual cross-modal pedestrian information search (PIS) technique based on graph-text modal fusion. Initially, we used a combination of replacement neural networks to improve the English Language-Based Pedestrian Information Search model with Graph-Text Modal Fusion (GTMFLPIS) performance. In addition, existing research lacks GTMFLPIS models for other languages. Therefore, we propose to train GTMFLPIS models for Chinese. The Chinese GTMFLPIS model was trained using our previously constructed Chinese CUHK-PEDES dataset. The Rank1 of the Chinese RN50_PMML12V2 model reached 0.5989. In addition, we found that a single model could not adapt to the limitations of multiple languages. Therefore, we propose a novel architecture to implement a single-model multilingual cross-modal GTMFLPIS model in this research. We propose RN50_DBMCV2 and ENB7_DBM-CV2, both of which have improved performance over the existing ones. We constructed a bilingual dataset using our Chinese CUHK-PEDES dataset and existing English CUHK-PEDES dataset to test our novel multilingual cross-modal GTMFLPIS model. In addition, we found that the loss function significantly impacts the model during our experiments. Therefore, we optimized the performance of the existing loss functions for cross-modal GTMFLPIS models. Our proposed CCMPM loss function improves the performance of the model by 2%. The experimental results of this research show that our proposed model has advantages in improving the accuracy of PIS.

Ensemble Transfer Learning for Image Classification

Nayan Kumar Sarkar — 2024-11-16

The deep learning (DL) techniques used for image classification might not deliver the desired level of classification accuracy as some features belonging to some class of a dataset are missed during feature extraction. The ensemble learning (EL) based model improves classification accuracy by combining the strengths of individual classifiers. As a result, those features that were missed during feature extraction by a specific DL technique will be taken care of by another DL technique in an ensemble DL approach. In this paper, averaging EL (AENet), weighted averaging EL (WAENet), and stacking EL (StackedNet) approaches are proposed, considering the DenseNet201, EcientNetB0, and ResNetRS101 as base models. The predictions of the base models are averaged to generate the AENet. The WAENet is constructed by assigning weights to each base model based on their prediction and then taking their average. Similarly, the Stacked-Net is developed by considering the DenseNet201, EcientNetB0, and ResNetRS101 as base-learners and ResNetRS101 as meta-learner. Analysed performance of the considered pre-trained base models and the developed EL models on the standard and application-specific datasets such as MiniImageNet, CIFAR10, CIFAR100, Plant Village (PV), Tomato, Covid-19 and 9IndianFood. 80% of the datasets were used to train and 20% to test the base and proposed models. The models are trained for an epoch of 30, considering a learning rate of 0.001 and adam optimizer. The stackedNet delivered better results than others.