Diffusion Facial Forgery Detection
- URL: http://arxiv.org/abs/2401.15859v1
- Date: Mon, 29 Jan 2024 03:20:19 GMT
- Title: Diffusion Facial Forgery Detection
- Authors: Harry Cheng and Yangyang Guo and Tianyi Wang and Liqiang Nie and Mohan
Kankanhalli
- Abstract summary: This paper introduces DiFF, a comprehensive dataset dedicated to face-focused diffusion-generated images.
We conduct extensive experiments on the DiFF dataset via a human test and several representative forgery detection methods.
The results demonstrate that the binary detection accuracy of both human observers and automated detectors often falls below 30%.
- Score: 56.69763252655695
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Detecting diffusion-generated images has recently grown into an emerging
research area. Existing diffusion-based datasets predominantly focus on general
image generation. However, facial forgeries, which pose a more severe social
risk, have remained less explored thus far. To address this gap, this paper
introduces DiFF, a comprehensive dataset dedicated to face-focused
diffusion-generated images. DiFF comprises over 500,000 images that are
synthesized using thirteen distinct generation methods under four conditions.
In particular, this dataset leverages 30,000 carefully collected textual and
visual prompts, ensuring the synthesis of images with both high fidelity and
semantic consistency. We conduct extensive experiments on the DiFF dataset via
a human test and several representative forgery detection methods. The results
demonstrate that the binary detection accuracy of both human observers and
automated detectors often falls below 30%, shedding light on the challenges in
detecting diffusion-generated facial forgeries. Furthermore, we propose an edge
graph regularization approach to effectively enhance the generalization
capability of existing detectors.
Related papers
- Semi-Truths: A Large-Scale Dataset of AI-Augmented Images for Evaluating Robustness of AI-Generated Image detectors [62.63467652611788]
We introduce SEMI-TRUTHS, featuring 27,600 real images, 223,400 masks, and 1,472,700 AI-augmented images.
Each augmented image is accompanied by metadata for standardized and targeted evaluation of detector robustness.
Our findings suggest that state-of-the-art detectors exhibit varying sensitivities to the types and degrees of perturbations, data distributions, and augmentation methods used.
arXiv Detail & Related papers (2024-11-12T01:17:27Z) - UGAD: Universal Generative AI Detector utilizing Frequency Fingerprints [18.47018538990973]
Our study introduces a novel multi-modal approach to detect AI-generated images.
Our approach significantly enhances the accuracy of differentiating between real and AI-generated images.
arXiv Detail & Related papers (2024-09-12T10:29:37Z) - StealthDiffusion: Towards Evading Diffusion Forensic Detection through Diffusion Model [62.25424831998405]
StealthDiffusion is a framework that modifies AI-generated images into high-quality, imperceptible adversarial examples.
It is effective in both white-box and black-box settings, transforming AI-generated images into high-quality adversarial forgeries.
arXiv Detail & Related papers (2024-08-11T01:22:29Z) - Text Modality Oriented Image Feature Extraction for Detecting Diffusion-based DeepFake [32.237169711785896]
diffusion-based DeepFakes pose significant risks to the integrity and safety of online information.
We propose a text modality-oriented feature extraction method, termed TOFE.
Experiments conducted across ten diffusion types demonstrate the efficacy of our proposed method.
arXiv Detail & Related papers (2024-05-28T11:29:30Z) - Trinity Detector:text-assisted and attention mechanisms based spectral fusion for diffusion generation image detection [3.8473504915778745]
Trinity Detector incorporates coarse-grained text features through a CLIP encoder, coherently integrating them with fine-grained artifacts in the pixel domain for comprehensive multimodal detection.
Our performance is competitive across all datasets and up to 17.6% improvement in transferability in the diffusion datasets.
arXiv Detail & Related papers (2024-04-26T08:50:35Z) - DiffusionFace: Towards a Comprehensive Dataset for Diffusion-Based Face Forgery Analysis [71.40724659748787]
DiffusionFace is the first diffusion-based face forgery dataset.
It covers various forgery categories, including unconditional and Text Guide facial image generation, Img2Img, Inpaint, and Diffusion-based facial exchange algorithms.
It provides essential metadata and a real-world internet-sourced forgery facial image dataset for evaluation.
arXiv Detail & Related papers (2024-03-27T11:32:44Z) - Free-ATM: Exploring Unsupervised Learning on Diffusion-Generated Images
with Free Attention Masks [64.67735676127208]
Text-to-image diffusion models have shown great potential for benefiting image recognition.
Although promising, there has been inadequate exploration dedicated to unsupervised learning on diffusion-generated images.
We introduce customized solutions by fully exploiting the aforementioned free attention masks.
arXiv Detail & Related papers (2023-08-13T10:07:46Z) - Detecting Images Generated by Deep Diffusion Models using their Local
Intrinsic Dimensionality [8.968599131722023]
Diffusion models have been successfully applied for the visual synthesis of strikingly realistic appearing images.
This raises strong concerns about their potential for malicious purposes.
We propose using the lightweight multi Local Intrinsic Dimensionality (multiLID) for the automatic detection of synthetic images.
arXiv Detail & Related papers (2023-07-05T15:03:10Z) - Deceptive-NeRF/3DGS: Diffusion-Generated Pseudo-Observations for High-Quality Sparse-View Reconstruction [60.52716381465063]
We introduce Deceptive-NeRF/3DGS to enhance sparse-view reconstruction with only a limited set of input images.
Specifically, we propose a deceptive diffusion model turning noisy images rendered from few-view reconstructions into high-quality pseudo-observations.
Our system progressively incorporates diffusion-generated pseudo-observations into the training image sets, ultimately densifying the sparse input observations by 5 to 10 times.
arXiv Detail & Related papers (2023-05-24T14:00:32Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.