Training-free Detection of AI-generated Images via High-frequency Influence

Sungik Choi, Sungwoo Park, Jaehoon Lee, SeungHyun Kim, Stanley Jungkyu Choi, Moontae Lee

Keywords: Zero-shot detection, AI-generated image detection, Training-free, Deepfake detection, safety, LDM-generated image

TL;DR: We propose a universal score function that effectively distinguishes AI-generated images from real images in the zero-shot setting.

Abstract:

Dramatic advances in the quality of the latent diffusion models (LDMs) also led to the malicious use of AI-generated images. While current AI-generated image detection methods assume the availability of real/AI-generated images for training, this is practically limited given the vast expressibility of LDMs. This motivates the training-free detection setup where no related data are available in advance. In this paper, we propose that the level of aliasing detected in reconstructed images produced by the autoencoder of LDMs can serve as a criterion for distinguishing between real and AI-generated images. Specifically, we propose a novel detection score function, termed high-frequency influence (HFI), which quantifies the impact of the spatial filtering-based high-frequency components of the input image on the perceptual reconstruction distance. HFI is training-free, efficient, and consistently outperforms other training-free methods in detecting challenging images generated by various generative models. We also show that HFI can successfully detect the images generated from the specified LDM. HFI outperforms the best baseline method while achieving magnitudes of speedup.

Primary Area: alignment, fairness, safety, privacy, and societal considerations

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 5593