Link Prediction in Time-Evolving Criminal Network With Deep Reinforcement Learning Technique

Abstract

The prediction of hidden or missing links in a criminal network, which represent possible interactions between individuals, is a significant problem. The criminal network prediction models commonly rely on Social Network Analysis (SNA) metrics. These models leverage on machine learning (ML) techniques to enhance the predictive accuracy of the models and processing speed. The problem with the use of classical ML techniques such as support vector machine (SVM), is the dependency on the availability of large dataset for training purpose. However, recent ground breaking advances in the research of deep reinforcement learning (DRL) techniques have developed methods of training ML models through self-generated dataset. In view of this, DRL could be applied to other domains with relatively smaller dataset such as criminal networks. Prior to this research, few, if any, previous works have explored the prediction of links within criminal networks that could appear and/or disappear over time by leveraging on DRL technique. Therefore, in this paper, the primary objective is to construct a time-based link prediction model (TDRL) by leveraging on DRL technique to train using a relatively small real-world criminal dataset that evolves over time. The experimental results indicate that the predictive accuracy of the DRL model trained on the temporal dataset is significantly better than other ML models that are trained only with the dataset at specific snapshot in time. INDEX TERMS Social network analysis, link prediction performance, deep reinforcement learning, time-evolving network.

Peer Review #2 of "Classification of botnet attacks in IoT smart factory using honeypot combined with machine learning (v0.1)"

“…Applying machine learning in botnet detection for smart factories can become useful to enhance performance of the honeypot model in term of speeding up the processing time or detection time [21]. Interestingly, it is notified that very limited studies making attempts to mount both honeypot and machine learning on IoT device networks to target attack on the IoT traffic.…”

Comprehensive Review of Cybercrime Detection Techniques

“…Lim et al [81] utilized deep reinforcement learning (DRL) techniques to predict the missing and hidden relationship between the criminal in criminal network due to the lack of criminal databases. Only small criminal databases are available.…”

Security and Privacy Concerns in Wireless Networks - A Survey

“…[20] have proposed a data privacy-aware protocol to secure video reporting services used for roadside accident monitoring. Other solutions include authentication schemes [21]- [24], evaluation of available authentication techniques such as those proposed for healthcare domain which are highly sensitive [25], proposing secure routing protocols for wireless sensor network such as [26], energy efficient protocols which may play crucial role in energy security [27]- [29], highlighting the challenges of protocols for secure communication to address them [30], attack detection techniques [31], link prediction in criminal networks using techniques like deep reinforcement learning [32], phishing detection techniques [33]. Despite many efforts, networks are still prone to attacks, both internally and externally.…”