Can ChatGPT Perform Image Splicing Detection? A Preliminary Study

TL;DR

This study explores GPT-4V's ability to detect image splicing manipulations without fine-tuning, showing promising zero-shot performance and the ability to leverage contextual knowledge for forensic analysis.

Contribution

It demonstrates GPT-4V's out-of-the-box capabilities in image forensics, highlighting its potential as a flexible tool for splicing detection using various prompting strategies.

Findings

GPT-4V achieves over 85% accuracy in zero-shot detection.

Chain-of-Thought prompting improves detection balance.

Model uses contextual and visual cues for artifact identification.

Abstract

Multimodal Large Language Models (MLLMs) like GPT-4V are capable of reasoning across text and image modalities, showing promise in a variety of complex vision-language tasks. In this preliminary study, we investigate the out-of-the-box capabilities of GPT-4V in the domain of image forensics, specifically, in detecting image splicing manipulations. Without any task-specific fine-tuning, we evaluate GPT-4V using three prompting strategies: Zero-Shot (ZS), Few-Shot (FS), and Chain-of-Thought (CoT), applied over a curated subset of the CASIA v2.0 splicing dataset. Our results show that GPT-4V achieves competitive detection performance in zero-shot settings (more than 85% accuracy), with CoT prompting yielding the most balanced trade-off across authentic and spliced images. Qualitative analysis further reveals that the model not only detects low-level visual artifacts but also draws upon real-world contextual knowledge such as object scale, semantic consistency, and architectural facts, to identify implausible composites. While GPT-4V lags behind specialized state-of-the-art splicing detection models, its generalizability, interpretability, and encyclopedic reasoning highlight its potential as a flexible tool in image forensics.