TripletViNet: Mitigating Misinformation Video Spread Across Platforms
Petar Smolovic, Thilini Dahanayaka, Kanchana Thilakarathna
TL;DR
This work tackles the problem of identifying misinformation videos across multiple platforms from encrypted streaming traffic, addressing the limitations of single-platform fingerprinting. It proposes TripletViNet, a three-component framework that uses platform-wise pre-processing, a triplet-loss–based encoder, and a KNN classifier to learn video-specific embeddings that generalize across platforms. The authors collect a large dataset of 12k traces for 100 videos across six platforms and demonstrate that triplet learning yields roughly a 2–3x gain in closed-set cross-platform accuracy, with certain platform pairs reaching near-perfect performance. Open-set results show that known-class precision can approach ~80% for some platform pairs under thresholding, while overall performance remains challenging for unseen videos. The findings support network-level, cross-platform moderation strategies and establish a foundation for further cross-platform fingerprinting research and robust, platform-agnostic content identification.
Abstract
There has been rampant propagation of fake news and misinformation videos on many platforms lately, and moderation of such content faces many challenges that must be overcome. Recent research has shown the feasibility of identifying video titles from encrypted network traffic within a single platform, for example, within YouTube or Facebook. However, there are no existing methods for cross-platform video recognition, a crucial gap that this works aims to address. Encrypted video traffic classification within a single platform, that is, classifying the video title of a traffic trace of a video on one platform by training on traffic traces of videos on the same platform, has significant limitations due to the large number of video platforms available to users to upload harmful content to. To attempt to address this limitation, we conduct a feasibility analysis into and attempt to solve the challenge of recognizing videos across multiple platforms by using the traffic traces of videos on one platform only. We propose TripletViNet, a framework that encompasses i) platform-wise pre-processing, ii) an encoder trained utilizing triplet learning for improved accuracy and iii) multiclass classifier for classifying the video title of a traffic trace. To evaluate the performance of TripletViNet, a comprehensive dataset with traffic traces for 100 videos on six major platforms with the potential for spreading misinformation such as YouTube, X, Instagram, Facebook, Rumble, and Tumblr was collected and used to test TripletViNet in both closed-set and open-set scenarios. TripletViNet achieves significant improvements in accuracy due to the correlation between video traffic and the video's VBR, with impressive final accuracies exceeding 90% in certain scenarios.