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

页码：5125 / 5142

页数：18

共 50 条

[41] Improving visual grounding with multi-scale discrepancy information and centralized-transformer
Wu, Jie
Wu, Chunlei
Wang, Fuyan
Wang, Leiquan
Wei, Yiwei
EXPERT SYSTEMS WITH APPLICATIONS, 2024, 247
[42] Improving health equity: Evaluation of accessible written medication information for patients with visual impairment
Nguyen, Cambrey
JOURNAL OF THE AMERICAN PHARMACISTS ASSOCIATION, 2024, 64 (03)
[43] Improving Information Extraction from Visually Rich Documents using Visual Span Representations
Sarkhel, Ritesh
Nandi, Arnab
PROCEEDINGS OF THE VLDB ENDOWMENT, 2021, 14 (05): : 822 - 834
[44] Improving Response Time of Active Speaker Detection using Visual Prosody Information Prior to Articulation
Haider, Fasih
Luz, Saturnino
Vogel, Carl
Campbell, Nick
19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6: SPEECH RESEARCH FOR EMERGING MARKETS IN MULTILINGUAL SOCIETIES, 2018, : 1736 - 1740
[45] Improving readability of an evaluation tool for low-income clients using visual information processing theories
Townsend, Marilyn S.
Sylva, Kathryn
Martin, Anna
Metz, Diane
Wooten-Swanson, Patti
JOURNAL OF NUTRITION EDUCATION AND BEHAVIOR, 2008, 40 (03) : 181 - 186
[46] Improving Spatial Perception in Telepresence and Teleaction Systems by Displaying Distance Information through Visual and Vibrotactile Feedback
Cha, Jongeun
Barghout, Ahmad
Kammerl, Julius
Steinbach, Eckehard
El Saddik, Abdulmotaleb
PRESENCE-TELEOPERATORS AND VIRTUAL ENVIRONMENTS, 2010, 19 (05) : 430 - 449
[47] Improving visual function diagnostic metrics with the use of higher-order aberration information from the eye
Campbell, CE
JOURNAL OF REFRACTIVE SURGERY, 2004, 20 (05) : S495 - S503
[48] Visual storytelling for improving the comprehension and utility in disseminating information systems research: Evidence from a quasi-experiment
Mirkovski, Kristijan
Gaskin, James E.
Hull, David M.
Lowry, Paul Benjamin
INFORMATION SYSTEMS JOURNAL, 2019, 29 (06) : 1153 - 1177
[49] Improving orthodontic patients' and parents' information recall with use of audio-visual presentation and mind mapping exercises
Kaur Gakhal M.
Kwon O.
Evidence-Based Dentistry, 2020, 21 (1) : 34 - 35
[50] Towards improving visual-facial emotion recognition through use of complementary keyboard-stroke pattern information
Tsihrintzis, George A.
Virvou, Maria
Alepis, Efthymios
Stathopoulou, Ioanna-Ourania
PROCEEDINGS OF THE FIFTH INTERNATIONAL CONFERENCE ON INFORMATION TECHNOLOGY: NEW GENERATIONS, 2008, : 32 - 37

← 1 2 3 4 5 →