Provenance filtering and analysis

• Grant number: 20/02211-2
• Support Opportunities: Scholarships in Brazil - Doctorate (Direct)
• Effective date (Start): May 01, 2020
• Effective date (End): November 30, 2023
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Anderson de Rezende Rocha
• Grantee: João Phillipe Cardenuto
• Host Institution: Instituto de Computação (IC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
• Associated research grant: 17/12646-3 - Déjà vu: feature-space-time coherence from heterogeneous data for media integrity analytics and interpretation of events, AP.TEM

Abstract

In this research, we are mainly aimed at answering the question of how to find possible relationships among images from different moments in time (e.g., how different image pieces contribute to create a composite one). This research will allow the development of a series of solutions to analyze the provenance of a visual asset allowing us to check its veracity and to pinpoint the pieces that contributed to its creation process in the case of a composite/fake. Such tools will be invaluable for evaluating how different media objects are related digitally and physically, analyzing group dynamics, and even fact-checking published news articles using their pictures as a proxy for veracity checking against fake news. (AU)

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

CARDENUTO, JOAO P.; ROCHA, ANDERSON. Benchmarking Scientific Image Forgery Detectors. SCIENCE AND ENGINEERING ETHICS, v. 28, n. 4, p. 38-pg., 2022-08-01. (17/12646-3, 20/02211-2)

NASCIMENTO, JOSE; CARDENUTO, JOAO PHILLIPE; YANG, JING; ROCHA, ANDERSON; IEEE. Few-shot Learning for Multi-modal Social Media Event Filtering. 2022 IEEE INTERNATIONAL WORKSHOP ON INFORMATION FORENSICS AND SECURITY (WIFS), v. N/A, p. 6-pg., 2022-01-01. (17/12646-3, 20/02241-9, 20/02211-2, 19/04053-8)