Data collection and baselines implementation for detection of image scientific forgeries

• Grant number: 25/26481-2
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: February 01, 2026
• End date: January 31, 2027
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Anderson de Rezende Rocha
• Grantee: Diego Martins Santos
• Host Institution: Instituto de Computação (IC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
• Associated research grant: 23/12865-8 - Horus: artificial intelligence techniques to detect and forestall synthetic realities, AP.TEM

Abstract

This undergrad research has two objectives: benchmark dataset definition and baseline implementation for scientific forgery detection. Initially, we will build a benchmark dataset by collecting data from various repositories of retracted papers and utilizing existing image generators to create synthetic scientific images. Second, we seek to establish baselines for AI-generated forgery detection, which involves the implementation of state-of-the-art forgery detectors for general images, excluding scientific experiments. (AU)