Non-Semantic Evaluation of Image Forensics Tools: Methodology and Database

TL;DR

This paper introduces a methodology for creating challenging non-semantic image forgeries and presents a new database to evaluate forensic tools, highlighting their limitations in detecting subtle alterations.

Contribution

The paper proposes a novel methodology for generating non-semantic forgeries and introduces the Trace database for benchmarking forensic tools.

Findings

State-of-the-art forensic tools struggle to detect the created forgeries.

The Trace database provides a challenging benchmark for future forensic research.

The methodology isolates forgery cues from semantic content, focusing on technical alterations.

Abstract

With the aim of evaluating image forensics tools, we propose a methodology to create forgeries traces, leaving intact the semantics of the image. Thus, the only forgery cues left are the specific alterations of one or several aspects of the image formation pipeline. This methodology creates automatically forged images that are challenging to detect for forensic tools and overcomes the problem of creating convincing semantic forgeries. Based on this methodology, we create the Trace database and conduct an evaluation of the main state-of-the-art image forensics tools.