Robust Spammer Detection Using Collaborative Neural Network in Internet-of-Things Applications

Abstract

Spamming is emerging as a key threat to Internet of Things (IoT)-based social media applications. It will pose serious security threats to the IoT cyberspace. To this end, artificial intelligence-based detection and identification techniques have been widely investigated. The literature works on IoT cyberspace can be categorized into two categories: 1) behavior pattern-based approaches; and 2) semantic pattern-based approaches. However, they are unable to effectively handle concealed, complicated, and changing spamming activities, especially in the highly uncertain environment of the IoT. To address this challenge, in this paper, we exploit the collaborative awareness of both patterns, and propose a Collaborative neural network-based Spammer detection mechanism (Co-Spam) in social media applications. In particular, it introduces multi-source information fusion by collaboratively encoding long-term behavioral and semantic patterns. Hence, a more comprehensive representation of the feature space can be captured for further spammer detection. Empirically, we implement a series of experiments on two real-world datasets under different scenario and parameter settings. The efficiency of the proposed Co-Spam is compared with five baselines with respect to several evaluation metrics. The experimental results indicate that the Co-Spam has an average performance improvement of approximately 5% compared to the baselines.

High-Quality Coarse-to-Fine Fruit Detector for Harvesting Robot in Open Environment

“…During the recent years, deep learning based methods have made remarkable progress in many fileds [24], such as Internet of Things [25,26], Signal processing [27,28], UAV [29], wireless communications [30], and especially in the field of agriculture [31][32][33][34][35]. These include fruit classification [36][37][38], yield estimation and counting [39,40].…”

A Lightweight and Secured Certificate-Based Proxy Signcryption (CB-PS) Scheme for E-Prescription Systems

“…Also, it is not suffering from certificate management issue, key escrow issue, public key replacement issue, and secure channel need problem. The new scheme ensured the security requirements, i.e., Warrant Unforgeability, Confidentiality, Integrity, Unforgeability, Forward Secrecy, and Resists Replay Attack [41,42,43,44], respectively. Our scheme is not affected by heavy computation because we used hyper elliptic curve instead of bilinear pairing and elliptic curve which need very miner time for computations [11,12].…”

Fitness Monitoring System Based on Internet of Things and Big Data Analysis

“…The perception layer is mainly responsible for perception and data collection. It senses and monitors surrounding things and events through sensor collection nodes and obtains corresponding data [36][37][38]. It lies at the bottom of the three-tier system architecture of the Internet of Things.…”