RAID: A Dataset for Testing the Adversarial Robustness of AI-Generated Image Detectors
cs.CV, cs.LG
Submitted: 2025-06-04
Updated: 2026-10-29
Comments: 24 pages, 5 figures. Updated version: RAID dataset now contains 216k transferable adversarial images (PGD, APGD, and CWA attack splits), and evaluations on five additional unseen detectors
Code: https://github.com/pralab/RAID
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Synthetic Data from Diffusion Models Improves ImageNet Classification
- Real-Time Deepfake Detection in the Real-World
- Adversarial Robustness of AI-Generated Image Detectors in the Real World
- SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
- Characteristics and prevalence of fake social media profiles with AI-generated faces
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs