computer-vision-5

Fake Image Detection

3260 papers • 126 benchmarks • 313 datasets

( Image credit: FaceForensics++ )

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in fake-image-detection-5

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find fake-image-detection-5 models and implementations

Datasets

ArtiFact

Corn Seeds Dataset

Subtasks

GAN image forensics Fake Image Attribution

Most implemented papers

FaceForensics++: Learning to Detect Manipulated Facial Images

M. Nießner, C. Riess, Justus Thies, D. Cozzolino, L. Verdoliva, Andreas Rössler•Thu Jan 24 2019

This paper proposes an automated benchmark for facial manipulation detection, and shows that the use of additional domain-specific knowledge improves forgery detection to unprecedented accuracy, even in the presence of strong compression, and clearly outperforms human observers.

2677

Content

0

Paper Graph

MesoNet: a Compact Facial Video Forgery Detection Network

J. Yamagishi, I. Echizen, Darius Afchar, Vincent Nozick•Mon Sep 03 2018

A method to automatically and efficiently detect face tampering in videos, and particularly focuses on two recent techniques used to generate hyper-realistic forged videos: Deepfake and Face2Face.

1540 0

Paper Graph

ManTra-Net: Manipulation Tracing Network for Detection and Localization of Image Forgeries With Anomalous Features

Yue Wu, Wael AbdAlmageed, P. Natarajan•Fri May 31 2019

To fight against real-life image forgery, which commonly involves different types and combined manipulations, we propose a unified deep neural architecture called ManTra-Net. Unlike many existing solutions, ManTra-Net is an end-to-end network that performs both detection and localization without extra preprocessing and postprocessing. \manifold{} is a fully convolutional network and handles images of arbitrary sizes and many known forgery types such splicing, copy-move, removal, enhancement, and even unknown types. This paper has three salient contributions. We design a simple yet effective self-supervised learning task to learn robust image manipulation traces from classifying 385 image manipulation types. Further, we formulate the forgery localization problem as a local anomaly detection problem, design a Z-score feature to capture local anomaly, and propose a novel long short-term memory solution to assess local anomalies. Finally, we carefully conduct ablation experiments to systematically optimize the proposed network design. Our extensive experimental results demonstrate the generalizability, robustness and superiority of ManTra-Net, not only in single types of manipulations/forgeries, but also in their complicated combinations.

581 0

Paper Graph

Video Face Manipulation Detection Through Ensemble of CNNs

Nicolò Bonettini, Edoardo Daniele Cannas, S. Mandelli, L. Bondi, Paolo Bestagini, S. Tubaro•Wed Apr 15 2020

This paper studies the ensembling of different trained Convolutional Neural Network (CNN) models and shows that combining these networks leads to promising face manipulation detection results on two publicly available datasets with more than 119000 videos.

259 0

Paper Graph

Learning to Detect Fake Face Images in the Wild

Chia-Yen Lee, Chih-Chung Hsu, Yi-Xiu Zhuang•Sun Sep 23 2018

A deep forgery discriminator (DeepFD) to efficiently and effectively detect the computer-generated images and adopt contrastive loss in seeking the typical features of the synthesized images generated by different GANs and follow by concatenating a classifier to detect such computer- generated images.

120 0

Paper Graph

Global Texture Enhancement for Fake Face Detection in the Wild

Philip H. S. Torr, Jiaya Jia, Zhengzhe Liu, Xiaojuan Qi•Fri Jan 31 2020

A new architecture coined as Gram-Net, which leverages global image texture representations for robust fake image detection and generalizes significantly better in detecting fake faces from GAN models not seen in the training phase and can perform decently in detectingfake natural images.

391 0

Paper Graph

FakePolisher: Making DeepFakes More Detection-Evasive by Shallow Reconstruction

Qing Guo, Yang Liu, Felix Juefei-Xu, L. Ma, Xiaofei Xie, Yihao Huang, Run Wang, Jianwen Li, Weikai Miao, G. Pu•Fri Jun 12 2020

Through reducing artifact patterns, the FakePolisher technique significantly reduces the accuracy of the 3 state-of-the-art fake image detection methods, i.e., 47% on average and up to 93% in the worst case.

89 0

Paper Graph

Learning on Gradients: Generalized Artifacts Representation for GAN-Generated Images Detection

Yunchao Wei, Shikui Wei, Chuangchuang Tan, Yao Zhao, Guanghua Gu•Wed May 31 2023

Recently, there has been a significant advancement in image generation technology, known as GAN. It can easily generate realistic fake images, leading to an increased risk of abuse. However, most image detectors suffer from sharp performance drops in unseen domains. The key of fake image detection is to develop a generalized representation to describe the artifacts produced by generation models. In this work, we introduce a novel detection framework, named Learning on Gradients (LGrad), designed for identifying GAN-generated images, with the aim of constructing a generalized detector with cross-model and cross-data. Specifically, a pretrained CNN model is employed as a transformation model to convert images into gradients. Subsequently, we leverage these gradients to present the generalized artifacts, which are fed into the classifier to ascertain the authenticity of the images. In our framework, we turn the data-dependent problem into a transformation-model-dependent problem. To the best of our knowledge, this is the first study to utilize gradients as the representation of artifacts in GAN-generated images. Extensive experiments demonstrate the effectiveness and robustness of gradients as generalized artifact representations. Our detector achieves a new state-of-the-art performance with a remarkable gain of 11.4%. The code is released at https://github.com/chuangchuangtan/LGrad.

212 0

Paper Graph

Unveiling the Truth: Exploring Human Gaze Patterns in Fake Images

Marcella Cornia, R. Cucchiara, Giuseppe Cartella, Vittorio Cuculo•Tue Mar 12 2024

This work collects a novel dataset of partially manipulated images using diffusion models and conducts an eye-tracking experiment to record the eye movements of different observers while viewing real and fake stimuli to explore the distinctive patterns in how humans perceive genuine and altered images.

13 0

Paper Graph

Parents and Children: Distinguishing Multimodal Deepfakes from Natural Images

Marcella Cornia, L. Baraldi, R. Cucchiara, A. Bimbo, Davide Morelli, Roberto Amoroso•Sat Apr 01 2023

This work pioneer a systematic study on deepfake detection generated by state-of-the-art diffusion models, and introduces a contrastive-based disentangling method that lets us analyze the role of the semantics of textual descriptions and low-level perceptual cues.

35 0

Paper Graph

Adding a benchmark result helps the community track progress.