SISL:Self-Supervised Image Signature Learning for Splicing Detection & Localization

@article{Agrawal2022SISLSelfSupervisedIS,
  title={SISL:Self-Supervised Image Signature Learning for Splicing Detection \& Localization},
  author={Susmit Agrawal and Prabhat Kumar and Siddharth Seth and Toufiq Parag and Maneesh Kumar Singh and R. Venkatesh Babu},
  journal={2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  year={2022},
  pages={22-32}
}
Recent algorithms for image manipulation detection almost exclusively use deep network models. These approaches require either dense pixelwise groundtruth masks, camera ids, or image metadata to train the networks. On one hand, constructing a training set to represent the countless tampering possibilities is impractical. On the other hand, social media platforms or commercial applications are often constrained to remove camera ids as well as metadata from images. A self-supervised algorithm for… 

Figures and Tables from this paper

Three-stage image forgery localization with shallow feature enhancement and attention

Extensive experimental results show that this method outperforms other state-of-the-art methods in image forgery localization, making full use of local and global information to improve the generalization ability.

References

SHOWING 1-10 OF 81 REFERENCES

Fighting Fake News: Image Splice Detection via Learned Self-Consistency

A learning algorithm for detecting visual image manipulations that is trained only using a large dataset of real photographs to determine whether an image is self-consistent — that is, whether its content could have been produced by a single imaging pipeline.

Deep Matching and Validation Network: An End-to-End Solution to Constrained Image Splicing Localization and Detection

A novel deep convolutional neural network architecture, called Deep Matching and Validation Network (DMVN), which simultaneously localizes and detects image splicing and is end-to-end optimized to produce the probability estimates and the segmentation masks.

CAT-Net: Compression Artifact Tracing Network for Detection and Localization of Image Splicing

CAT-Net is proposed, an end-to-end fully convolutional neural network including RGB and DCT streams, to learn forensic features of compression artifacts on RGB andDCT domains jointly to localize spliced regions in JPEG or non-JPEG images.

Noiseprint: A CNN-Based Camera Model Fingerprint

This paper proposes a method to extract a camera model fingerprint, called noiseprint, where the scene content is largely suppressed and model-related artifacts are enhanced, by means of a Siamese network trained with pairs of image patches coming from the same or different cameras.

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

An algorithm for image tampering detection and localization, leveraging characteristic footprints left on images by different camera models to detect whether an image has been forged, and localize the alien region.

Leveraging Frequency Analysis for Deep Fake Image Recognition

It is demonstrated how the frequency representation can be used to identify deep fake images in an automated way, surpassing state-of-the-art methods.

Learning Rich Features for Image Manipulation Detection

A two-stream Faster R-CNN network is proposed and trained end-to-end to detect the tampered regions given a manipulated image and fuse features from the two streams through a bilinear pooling layer to further incorporate spatial co-occurrence of these two modalities.

Extracting camera-based fingerprints for video forensics

A neural network is trained that enhances the model-related traces hidden in a video, extracting a sort of camera fingerprint, called video noiseprint, that performs well in major forensic tasks, such as camera model identification and video forgery localization, with no need of prior knowledge on the specific manipulation or any form of fine-tuning.

RRU-Net: The Ringed Residual U-Net for Image Splicing Forgery Detection

The core idea of the proposed RRU-Net is to strengthen the learning way of CNN, which is inspired by the recall and the consolidation mechanism of the human brain and implemented by the propagation and the feedback process of the residual in CNN.
...