PIXELMOD: Improving Soft Moderation of Visual Misleading Information on Twitter

被引：0
|
作者：
Paudel, Pujan [1 ]
Ling, Chen [1 ]
Blackburn, Jeremy [2 ]
Stringhini, Gianluca [1 ]
机构：
[1] Boston Univ, Boston, MA 02215 USA
[2] SUNY Binghamton, Binghamton, NY 13902 USA
来源：
PROCEEDINGS OF THE 33RD USENIX SECURITY SYMPOSIUM, SECURITY 2024 | 2024年
关键词：
D O I：
暂无
中图分类号：
学科分类号：
摘要：
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.
引用
收藏
页码：5125 / 5142
页数：18
相关论文
共 50 条
  • [31] Improving Performance of Medical Images Retrieval by Combining Textual and Visual Information
    Diaz-Galiano, M. C.
    Martin-Valdivia, M. T.
    Montejo-Raez, A.
    Urena-Lopez, L. A.
    MICAI 2007: SIXTH MEXICAN INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE, PROCEEDINGS, 2008, : 185 - 192
  • [32] Misleading information in crises: exploring content-specific indicators on Twitter from a user perspective(jun, 10.1080/0144929X.2024.2373166, 2024)
    Hartwig, K.
    Schmid, S.
    Biselli, T.
    Pleil, H.
    Reuter, C.
    BEHAVIOUR & INFORMATION TECHNOLOGY, 2024,
  • [33] A Meta-Analysis of Vibrotactile and Visual Information Displays for Improving Task Performance
    Prewett, Matthew S.
    Elliott, Linda R.
    Walvoord, Ashley G.
    Coovert, Michael D.
    IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART C-APPLICATIONS AND REVIEWS, 2012, 42 (01): : 123 - 132
  • [34] Improving Relevance of Keyword Extraction from the Web Utilizing Visual Style Information
    Lucansky, Milan
    Simko, Marian
    SOFSEM 2013: THEORY AND PRACTICE OF COMPUTER SCIENCE, 2013, 7741 : 445 - 456
  • [35] Adjustable Properties of Visual Representations: Improving the Quality of Human-Information Interaction
    Parsons, Paul
    Sedig, Kamran
    JOURNAL OF THE ASSOCIATION FOR INFORMATION SCIENCE AND TECHNOLOGY, 2014, 65 (03) : 455 - 482
  • [36] Improving Memory after Interruption: Exploiting Soft Constraints and Manipulating Information Access Cost
    Morgan, Phillip L.
    Patrick, John
    Waldron, Samuel M.
    King, Sophia L.
    Patrick, Tanya
    JOURNAL OF EXPERIMENTAL PSYCHOLOGY-APPLIED, 2009, 15 (04) : 291 - 306
  • [37] Improving Visual Style Classification Information in Digital Games Using Intercoder Reliability Assessment
    Jamal, Jazmi Izwan
    Yusof, Mohd Hafizuddin Mohd
    Yoong, Lim Kok
    Jamal, Jamia Azdina
    JOURNAL OF INFORMATION AND COMMUNICATION TECHNOLOGY-MALAYSIA, 2023, 22 (02): : 283 - 308
  • [38] IMPROVING HEALTH EDUCATION FOR BRAIN TUMOR PATIENTS AND RELATIVES THROUGH ANIMATED AND VISUAL INFORMATION
    Baas-Thijssen, M. C.
    Nogarede-Bloemendaal, C. O.
    Docter-Kerkhof, C. S.
    NEURO-ONCOLOGY, 2024, 26 : V29 - V29
  • [39] Integration of Visual Information and Robot Offline Programming System for Improving Automatic Deburring Process
    Lai, Zengliang
    Xiong, Rentao
    Wu, Hongmin
    Guan, Yisheng
    2018 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND BIOMIMETICS (ROBIO), 2018, : 1132 - 1137
  • [40] Improving the Accuracy and Speed of Visual Field Testing in Glaucoma With Structural Information and Deep Learning
    Montesano, Giovanni
    Lazaridis, Georgios
    Ometto, Giovanni
    Crabb, David P.
    Garway-Heath, David F.
    TRANSLATIONAL VISION SCIENCE & TECHNOLOGY, 2023, 12 (10):
12345