ML Security PapersPublished on arXiv
2512.21562
Output Integrity Attack
OWASP ML Top 10 — ML09
Key Finding
Detection performance drops sharply when preprocessing disrupts key features or when testing across unseen generators, revealing that current AIGC detectors lack generalizability due to generator-specific overfitting.
While the technology for detecting AI-Generated Content (AIGC) images has advanced rapidly, the field still faces two core issues: poor reproducibility and insufficient gen eralizability, which hinder the practical application of such technologies. This study addresses these challenges by re viewing 7 key papers on AIGC detection, constructing a lightweight test dataset, and reproducing a representative detection method. Through this process, we identify the root causes of the reproducibility dilemma in the field: firstly, papers often omit implicit details such as prepro cessing steps and parameter settings; secondly, most detec tion methods overfit to exclusive features of specific gener ators rather than learning universal intrinsic features of AIGC images. Experimental results show that basic perfor mance can be reproduced when strictly following the core procedures described in the original papers. However, de tection performance drops sharply when preprocessing dis rupts key features or when testing across different genera tors. This research provides empirical evidence for improv ing the reproducibility of AIGC detection technologies and offers reference directions for researchers to disclose ex perimental details more comprehensively and verify the generalizability of their proposed methods.
Key Contributions
- Reviews 7 key AIGC detection papers and identifies reproducibility gaps caused by omitted preprocessing steps and undisclosed parameter settings
- Constructs a lightweight test dataset for evaluating AIGC detection generalizability across different generators
- Provides empirical evidence that AIGC detectors overfit to generator-specific features rather than universal intrinsic AIGC features, causing sharp cross-generator performance drops
🛡️ Threat Analysis
AI-generated image detection is the central topic; the paper reviews, reproduces, and empirically evaluates AIGC detection methods, directly contributing to the content provenance and output integrity space.