← Back to all news
arXiv AI By Yulin Chen, Zeyuan Wang, Tianyuan Yu, Yingmei Wei, Liang Bai

FoCLIP: A Feature-Space Misalignment Framework for CLIP-Based Image Manipulation and Detection

Read the original on arXiv AI →

FoCLIP is a framework that creates adversarial examples to manipulate CLIP-based image quality metrics by reducing the alignment between image and text features. It uses stochastic gradient descent to combine feature alignment, score distribution balancing, and pixel‑guard regularization, enabling high CLIPscore predictions while maintaining visual fidelity. Experiments on artistic prompts and ImageNet show significant CLIPscore gains, and the authors also propose a color‑channel sensitivity detection method that achieves 91% accuracy.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

Hugging Face Trending Papers
Jul 29

CASIAL: Geometric Distortion Robust Image Watermarking

Deep learning-based watermarking has shown strong robustness against non-geometric distortions, yet its performance under geometric transformations remains limited. Such transformations induce two fundamental failure modes: region removal, such as cropping or masking, which eliminates the information carried by removed pixels, and desynchronization, such as scaling or rotation, which misaligns pixel positions and disrupts decoding.

safety
More like this →
arXiv Computer Vision
6d ago

FeatMark: Feature-level Watermark Protection against Mimicry Attacks with Diffusion Models

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.

By Haoyang Li, Ruoxi Sun, Qingqing Ye, Benjamin Zi Hao Zhao, Yaxin Xiao, Jason Xue, Haibo Hu
diffusionfine-tuningsafety
More like this →
arXiv AI
Jun 16

Decoupling Semantics from Distortions: Multi-Scale Two-Stream Vision-Language Alignment for AI-Generated Image Quality Assessment

arXiv:2606. 16799v1 Announce Type: cross Abstract: Existing vision-language model (VLM)-based AI-generated image quality assessment (AIGIQA) methods suffer from a fundamental semantic-distortion dimensional conflict: monolithic representations optimized for semantic discrimination inherently entangle compositional understanding with low-level perceptual sensitivity, rendering them blind to fine-grained quality degradations.

By Zijie Meng
llmsefficiencymultimodalbenchmarkssafety
More like this →