Applying Deep Learning to Combat Mass Robocalls

Pandit, Sharbani; Liu, Jienan; Perdisci, Roberto; Ahamad, Mustaque

doi:10.1109/spw53761.2021.00018

Cited by 3 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is worth noting that the feasibility of caller-ID spoofing varies between countries and regions. In countries with strict regulations, such as the United States (US) and the United Kingdom (UK), initiating a call with a spoofed caller-ID is extremely difficult [1], [9]. However, in countries with less regulation or oversight, such as developing countries, caller-ID spoofing is relatively simple.…”

Section: Introductionmentioning

confidence: 99%

Blockchain-Based Caller-ID Authentication (BBCA): A Novel Solution to Prevent Spoofing Attacks in VoIP/SIP Networks

Tas,

Baktir

2024

IEEE Access

View full text Add to dashboard Cite

Voice over Internet Protocol (VoIP) networks are vulnerable to caller-ID (calleridentification) spoofing attacks due to the open nature of Session Initiation Protocol (SIP) signaling. Caller-ID spoofing is a critical security threat in modern telecommunication systems, allowing attackers to impersonate legitimate callers and gain access to sensitive information. While these attacks pose a significant threat to the telecom and financial industries, the existing solutions are limited to only closedcircuit options for subscribers of the same service provider. In this paper, we present a novel blockchainbased solution to effectively prevent caller-ID spoofing attacks in real time. Our approach employs a lowlatency consensus algorithm to manage and verify end-to-end the caller-ID information of Internet Service Providers (ISPs) and institutions. We propose a two-step verification process, in which the accuracy and integrity of Automatic Number Identification (ANI) information is verified at different stages of the call. The proposed solution initiates a renewal of the ISP registration on every caller-ID change, making it unaffected by unusual situations such as roaming, the use of an IP-PBX (Internet Protocol Private Branch Exchange), or the use of a VPN (Virtual Private Network). We also discuss the proposed solution's feasibility and potential deployment issues, including its integration into existing RFC (Request for Comments) efforts and the necessary regulations for service providers to demonstrate compliance. Furthermore, we address future research directions, such as handling complex call scenarios such as call forwarding and teleconference calls. Our approach not only improves the security of telecommunication systems but also provides an efficient and scalable solution to prevent caller-ID spoofing attacks.

show abstract

Section: Introductionmentioning

confidence: 99%

Blockchain-Based Caller-ID Authentication (BBCA): A Novel Solution to Prevent Spoofing Attacks in VoIP/SIP Networks

Tas,

Baktir

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Those shady businesses may be more than just annoyances to customers; they could also be attempting to defraud them. The use of robocalls allows organizations to reach thousands of potential customers in a short amount of time, unlike traditional "live" telemarketing methods [5].…”

Section: Introductionmentioning

confidence: 99%

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

Akinyemi¹,

Odukoya²,

Sanni³

et al. 2022

IJCNIS

View full text Add to dashboard Cite

Many techniques have been proposed to detect and prevent spam over Internet telephony. Human spam calls can be detected more accurately with these techniques. However, robocalls, a type of voice spammer whose calling patterns are similar to those of legitimate users, cannot be detected as effectively. This paper proposes a model for robocall detection using a machine learning approach. Voice data recordings were collected and the relevant features for study were selected. The selected features were then used to formulate six (6) detection models. The formulated models were simulated and evaluated using some performance metrics to ascertain the model with the best performance. The C4.5 decision tree algorithm gave the best evaluation result with an accuracy of 99.15%, a sensitivity of 0.991%, a false alarm rate of 0.009%, and a precision of 0.992%. As a result, it was concluded that this approach can be used to detect and filter both machine-initiated and human-initiated spam calls.

show abstract