The Flow has not summarised this story yet — read it at arXiv Computer Vision.
The paper introduces VeriFi, a watermarking framework that protects face images from AI‑generated manipulation. It embeds a compact semantic latent watermark to preserve content, localizes pixel‑level edits without explicit payloads, and simulates realistic deepfake attacks to improve robustness. Experiments on CelebA‑HQ and FFHQ show that VeriFi outperforms existing methods in robustness, localization accuracy, and recovery quality.
FeatMark is a watermarking framework that protects images from text‑to‑image diffusion model mimicry attacks by embedding small, scene‑consistent micro‑features instead of pixel‑level perturbations. It constructs domain‑specific feature banks, selects executable features, and injects them via mask‑guided concept editing to create highly localized, natural edits. Experiments on VGGFace2, CelebA‑HQ, and WikiArt show FeatMark remains robust against ten strong watermark removal attacks and several adaptive attacks, with minimal impact on perceptual quality and extending to video mimicry scenarios.
The paper introduces Latent Frequency Masking, an attack that removes or weakens invisible watermarks in AI-generated images by altering selected Fourier coefficients in the latent space. It demonstrates that this method can effectively compromise six diffusion watermarking techniques while maintaining image quality and running faster than existing attacks. The study provides a theoretical distortion bound and evaluates the attack on images from DiffusionDB and MS-COCO prompts.
arXiv:2607. 28936v1 Announce Type: cross Abstract: Facial biometric identification relies on the distinctiveness of user attributes within a high-dimensional embedding space.
arXiv:2609.27022v1 Announce Type: new Abstract: In this paper, we investigate the impact of adversarial attacks on identity encoders within a realistic de-identification framework. Our experiments sh...
Text-to-image diffusion models enable data-efficient "mimicry" attacks, wherein adversaries fine-tune the model on a handful of public photos to synthesize convincing forgeries of a target individual....