Search papers, labs, and topics across Lattice.
This paper introduces CIPHER, a deepfake detection framework that reuses and fine-tunes discriminators from GANs and diffusion models to identify generation-agnostic artifacts. CIPHER extracts scale-adaptive features from ProGAN discriminators and temporal-consistency features from diffusion models, enabling it to generalize better across diverse generative models. Experiments show CIPHER achieves up to 74.33% F1-score, outperforming ViT-based detectors by over 30% on average and demonstrating robustness on challenging datasets where other methods fail.
By cleverly repurposing GAN and diffusion model discriminators, CIPHER achieves state-of-the-art deepfake detection that's robust to unseen generative models, leaving traditional detectors in the dust.
The rapid progress of generative adversarial networks (GANs) and diffusion models has enabled the creation of synthetic faces that are increasingly difficult to distinguish from real images. This progress, however, has also amplified the risks of misinformation, fraud, and identity abuse, underscoring the urgent need for detectors that remain robust across diverse generative models. In this work, we introduce Counterfeit Image Pattern High-level Examination via Representation(CIPHER), a deepfake detection framework that systematically reuses and fine-tunes discriminators originally trained for image generation. By extracting scale-adaptive features from ProGAN discriminators and temporal-consistency features from diffusion models, CIPHER captures generation-agnostic artifacts that conventional detectors often overlook. Through extensive experiments across nine state-of-the-art generative models, CIPHER demonstrates superior cross-model detection performance, achieving up to 74.33% F1-score and outperforming existing ViT-based detectors by over 30% in F1-score on average. Notably, our approach maintains robust performance on challenging datasets where baseline methods fail, with up to 88% F1-score on CIFAKE compared to near-zero performance from conventional detectors. These results validate the effectiveness of discriminator reuse and cross-model fine-tuning, establishing CIPHER as a promising approach toward building more generalizable and robust deep-fake detection systems in an era of rapidly evolving generative technologies.
