Pujan Paudel and Chen Ling, Boston University; Jeremy Blackburn, Binghamton University; Gianluca Stringhini, Boston University
Images are a powerful and immediate vehicle to carry misleading or outright false messages, yet identifying image-based misinformation at scale poses unique challenges. In this paper, we present PIXELMOD, a system that leverages perceptual hashes, vector databases, and optical character recognition (OCR) to efficiently identify images that are candidates to receive soft moderation labels on Twitter. We show that PIXELMOD outperforms existing image similarity approaches when applied to soft moderation, with negligible performance overhead. We then test PIXELMOD on a dataset of tweets surrounding the 2020 US Presidential Election, and find that it is able to identify visually misleading images that are candidates for soft moderation with 0.99% false detection and 2.06% false negatives.
Open Access Media
USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are posted after the event are also free and open to everyone. Support USENIX and our commitment to Open Access.
author = {Pujan Paudel and Chen Ling and Jeremy Blackburn and Gianluca Stringhini},
title = {{PIXELMOD}: Improving Soft Moderation of Visual Misleading Information on Twitter},
booktitle = {33rd USENIX Security Symposium (USENIX Security 24)},
year = {2024},
isbn = {978-1-939133-44-1},
address = {Philadelphia, PA},
pages = {5125--5142},
url = {https://www.usenix.org/conference/usenixsecurity24/presentation/paudel-pixelmod},
publisher = {USENIX Association},
month = aug
}
