Code-in-the-Loop Forensics: Agentic Tool Use for Image Forgery Detection

1. 1Combine low-level, semantics-agnostic artifacts with high-level semantic knowledge from multimodal large language models (MLLMs)
2. 2Develop agentic tool use for effective cross-level interactions between the two information streams
3. 3Implement code-in-the-loop forensics for image forgery detection
4. 4Evaluate the performance of the proposed method using relevant metrics

AI engineers and researchers on a team benefit from this approach as it enhances image forgery detection capabilities, and software engineers can implement the proposed method

💡 Combining low-level artifacts and high-level semantic knowledge can improve image forgery detection

💡 Code-in-the-Loop Forensics: Unifying low-level artifacts & high-level semantics for image forgery detection