Satellite Image Forgery Detection and Localization Using GAN and One-Class Classifier (2018-01-28T00:00:00.000000Z)

TL;DR

An algorithm for satellite image forgery detection and localization is proposed that works under the assumption that no forged images are available for training and is validated against different kinds of satellite images containing forgeries of different size and shape.

Abstract

Current satellite imaging technology enables shooting high-resolution pictures of the ground. As any other kind of digital images, overhead pictures can also be easily forged. However, common image forensic techniques are often developed for consumer camera images, which strongly differ in their nature from satellite ones (e.g., compression schemes, post-processing, sensors, etc.). Therefore, many accurate state-of-the-art forensic algorithms are bound to fail if blindly applied to overhead image analysis. Development of novel forensic tools for satellite images is paramount to assess their authenticity and integrity. In this paper, we propose an algorithm for satellite image forgery detection and localization. Specifically, we consider the scenario in which pixels within a region of a satellite image are replaced to add or remove an object from the scene. Our algorithm works under the assumption that no forged images are available for training. Using a generative adversarial network (GAN), we learn a feature representation of pristine satellite images. A one-class support vector machine (SVM) is trained on these features to determine their distribution. Finally, image forgeries are detected as anomalies. The proposed algorithm is validated against different kinds of satellite images containing forgeries of different size and shape.

Authors

E. Delp

4 papers

Paolo Bestagini

8 papers

S. Tubaro

8 papers

TL;DR

Abstract

Authors

References34 items

Aligned and Non-Aligned Double JPEG Detection Using Convolutional Neural Networks

Tampering Detection and Localization Through Clustering of Camera-Based CNN Features

A Counter-Forensic Method for CNN-Based Camera Model Identification

Identification of inpainted satellite images using evalutionary artificial neural network (EANN) and k-nearest neighbor(KNN) algorithm

Mask R-CNN

Autoencoder with recurrent neural networks for video forgery detection

Histogram Layer, Moving Convolutional Neural Networks Towards Feature-Based Steganalysis

Camera model identification with the use of deep convolutional neural networks

Single-image splicing localization through autoencoder-based anomaly detection

Double JPEG compression forensics based on a convolutional neural network

A Deep Learning Approach to Universal Image Manipulation Detection Using a New Convolutional Layer

Context Encoders: Feature Learning by Inpainting

Structural Design of Convolutional Neural Networks for Steganalysis

Camera identification with deep convolutional networks

Deep Residual Learning for Image Recognition

Deep Learning for steganalysis is better than a Rich Model with an Ensemble Classifier, and is natively robust to the cover source-mismatch

Median Filtering Forensics Based on Convolutional Neural Networks

Deep learning for steganalysis via convolutional neural networks

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

ImageNet Large Scale Visual Recognition Challenge

Information Forensics: An Overview of the First Decade

An Overview on Image Forensics

ImageNet classification with deep convolutional neural networks

Vision of the unseen: Current trends and challenges in digital image and video forensics

A semi-fragile pinned sine transform watermarking system for content authentication of satellite images

GENERATIVE ADVERSARIAL NETS

Conspiracy Files: Who shot down MH17

15 Free Satellite Imagery Data Sources

Deep Learning

Satellite images show clearly that Russia faked its MH17 report

He is currently pursuing a Ph.D. at the Video and Image Processing Laboratory (VIPER)

Visualizing Data using t-SNE

THE NATIONAL AERONAUTICS AND SPACE ADMINISTRATION

Geological Survey, USGS.gov -Science for a changing world

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names