logo

A Consensus Protocol for Incentivizing Contribution from Decentralized Community for Machine Learning-based Scamming Website Detection

RESEARCH CREW
17:54 08/06/2023

The increasing proliferation of phishing and scamming websites has become a significant threat to the safety and security of internet users. Accurately detecting such websites is crucial in mitigating their negative impact. While various techniques for detecting phishing and scamming websites exist, machine learning-based approaches have gained significant attention in recent years due to their promising results. However, ensuring the authenticity of the large datasets used to train the models is challenging. This paper proposes a blockchain and ML-based solution with a consensus algorithm named The Proof of Anti-scam (PoAS) that encourages and verifies data contributions from community members through a transparent incentivizing mechanism. Our experiments indicate that VGG16 is highly compatible with ML algorithms for accurately classifying phishing websites, and the PoAS consensus mechanism can work well in a large-scale network. This paper also highlights the potential benefits of using blockchain technology to incentivize data contributions to detect phishing and scamming websites more effectively.

TIN LIÊN QUAN
An Approach of Adaptive Cyber Deception for Active Cyber-attack Defense Method based on Deep Reinforcement Learning
The diverse landscape of network models, including Software-Defined Networking (SDN), Cloud Computing (C2), and Internet of Things (IoT), is evolving to meet the demands of flexibility and performance. However, these environments face numerous security challenges due to cyber-attack complexity. Traditional defense mechanisms are no longer effective against modern attacks. Therefore,...
Multimodal Deep Learning Feedback for Generating Evasive Malware Samples against Malware Detector
As data driven-based Windows malware detectors become increasingly prevalent, the need for robust evaluation and enhancement of adversarial malware generation techniques also becomes imperative, as malicious actors will adapt and enhance their malware to evade detection. There are numerous works that introduce new techniques or enhancements for adversarial malware. One...
Medichain: A multi-chain based system for managing prescription medications using Zero Knowledge Proofs
The abuse of prescription medications has become a severe public health crisis fueled by limited coordination and oversight across healthcare systems. Current frameworks lack interoperability between doctors, pharmacies, and regulators, enabling abusive practices like doctor shopping and pharmacy hopping. To address these issues, this research proposes Medichain, a novel multichain-based...