Detecting Nuisance Calls over Internet Telephony Using Caller Reputation

Abstract

Internet telephony permit callers to manage self-asserted profiles without any subscription contract nor identification proof. These cost-free services have attracted many telemarketers and spammers who generate unsolicited nuisance calls. Upon detection, they simply rejoin the network with a new identity to continue their malicious activities. Nuisance calls are highly disruptive when compared to email and social spam. They not only include annoying telemarketing calls but also contain scam and voice phishing which involves security risk for subscribers. Therefore, it remains a major challenge for Internet telephony providers to detect and avoid nuisance calls efficiently. In this paper, we present a new approach that uses caller reputation to detect different kinds of nuisance calls generated in the network. The reputation is computed in a hybrid manner by extracting information from call data records and using recommendations from reliable communicating participants. The behavior of the caller is assessed by extracting call features such as call-rate, call duration, and call density. Long term and short term reputations are computed to quickly detect the changing behavior of callers. Furthermore, our approach involves an efficient mechanism to combat whitewashing attacks performed by malicious callers to continue generating nuisance calls in the network. We conduct simulations to compute the performance of our proposed model. The experiments conclude that the proposed reputation model is an effective method to detect different types of nuisance calls while avoiding false detection of legitimate calls.

Detecting SPIT Attacks in VoIP Networks Using Convolutional Autoencoders: A Deep Learning Approach

“…The reputation model developed by Javed et al [4] was aimed at detecting spam callers in a network. The caller's reputation was computed in a hybrid manner by considering call features such as call density, call duration, and call rate from CDRs as well as recommendations from reliable callers.…”

“…According to the Cisco report, the number of networked devices will be about 29 billion by 2023 [3]. Meanwhile, VoIP users have become vulnerable to many attacks, such as SPIT detection [4]. SPIT is mostly used to promote items, annoy subscribers, induce users to call special numbers, or conduct vishing attempts to obtain private information from call participants [5].…”

Performance Evaluation of Machine Learning based Robocalls Detection Models in Telephony Networks

“…Voice over Internet Protocols (VoIPs) are becoming increasingly popular, and Spam over IP Telephony (SPIT) is expected to become an increasingly serious issue in the near future. These nuisance calls are considered far more bothersome than messages or social spam since they are produced in real-time and have a much greater impact on productivity [1]. There exists a means of transmitting unsolicited calls over the traditional Public Switched Telephone Volume 14 (2022), Issue 6 Network (PSTN), where such calls are commonly initiated by telemarketers.…”

“…The cost of sending SPIT is about three orders of magnitude less than traditional PSTN telemarketer calls. Thus, the pricing structure of Internet telephony remains a significant contributor to its growth [1].…”

Health-ID: A Blockchain-Based Decentralized Identity Management for Remote Healthcare

“…Moreover, the web-based IdM allows users to create self-asserted profiles without performing any identity proofing. Therefore, identity theft is becoming common on web applications to commit scams and frauds [7,8]. Furthermore, centralized IdM has several weaknesses in ensuring data security and privacy [9].…”