Jettisoning Junk Messaging in the Era of End-to-End Encryption: A Case Study of WhatsApp

TL;DR

This study investigates junk messaging on WhatsApp, analyzing a large dataset to understand content and sender behavior, and explores on-device detection methods that respect end-to-end encryption.

Contribution

It provides the first large-scale analysis of junk messaging on WhatsApp and proposes an on-device classification approach to detect junk content without compromising encryption.

Findings

Nearly 10% of messages are junk content.

Junk senders use diverse strategies, including changing phone numbers.

On-device classification can effectively detect junk messages.

Abstract

WhatsApp is a popular messaging app used by over a billion users around the globe. Due to this popularity, understanding misbehavior on WhatsApp is an important issue. The sending of unwanted junk messages by unknown contacts via WhatsApp remains understudied by researchers, in part because of the end-to-end encryption offered by the platform. We address this gap by studying junk messaging on a multilingual dataset of 2.6M messages sent to 5K public WhatsApp groups in India. We characterise both junk content and senders. We find that nearly 1 in 10 messages is unwanted content sent by junk senders, and a number of unique strategies are employed to reflect challenges faced on WhatsApp, e.g., the need to change phone numbers regularly. We finally experiment with on-device classification to automate the detection of junk, whilst respecting end-to-end encryption.