We investigate how to characterize semantic significance (SS) in detecting image manipulations (IMD) for media forensics. We introduce the Characterization of Seman-tic Impact for IMD (CSI-IMD) dataset, which focuses on localizing and evaluating the semantic impact of image manipulations to counter advanced generative techniques. Our evaluation of 10 state-of-the-art IMD and localization methods on CSI-IMD reveals key insights. Unlike existing datasets, CSI-IMD provides detailed semantic annotations beyond traditional manipulation masks, aiding in the development of new defensive strategies. The dataset features manipulations from advanced generation methods, offering various levels of semantic significance. It is divided into two parts: a gold-standard set of 1,000 manu-ally annotated manipulations with high-quality control, and an extended set of 500,000 automated manipulations for large-scale training and analysis. We also propose a new SS-focused task to assess the impact of semantically targeted manipulations. Our experiments show that current IMD methods struggle with manipulations created using stable diffusion, with TruFor and Cat-Net performing the best among those tested. The CSI-IMD dataset will become available at https://github.com/csiimd/csiimd.

Lin Ai, Tharindu Sandaruwan Kumarage, Amrita Bhattacharjee, Zizhou Liu, Zheng Hui, Michael S. Davinroy, James Cook, Laura Cassani, Kirill Trapeznikov, Matthias Kirchner, Arslan Basharat, Anthony Hoogs, Joshua Garland, Huan Liu, Julia Hirschberg. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

We demonstrate the estimation of image resampling parameters in a deep learning framework by regressing the rescaling factor of 64x64-sized patches on features learned directly from grayscale intensities by a convolutional neural network (CNN). Our end-to-end network design comprises a simple concatenation of 25 convolutional layers with small 3x3 receptive fields and largely abstains from the use of pooling. We report experimental results on a large set of rescaled patches, for which the proposed CNN outperforms state-of-the-art frequency-domain estimators particularly in the case of downscaling. A critical discussion of sensitivities to mismatch between training and testing data points to failure cases.

Existing forensic techniques for image manipulation localization crucially assume that probe pixels belong to one of exactly two classes, genuine or manipulated. This letter argues that this convention fuels mis-labeling particularly in unsupervised settings, where singular but genuine content or the presence of multiple distinct manipulations may easily induce non-optimal partitions of the feature space. We propose to relax constraints via a greedy n-ary clustering approach, which we instantiate exemplarily in the popular pixel descriptor space of residual co-occurrences. Experimental results on widely used public benchmark datasets highlight the benefits of our approach.

Steganographic security in empirical covers is best understood for grayscale images. However, the world, and almost all digital images of it, are more colorful. This paper extends the weighted stego-image (WS) steganalysis method to detect stego images produced from covers that exhibit traces of color filter array (CFA) interpolation, which is common for images acquired with digital cameras. The approach combines techniques of CFA forensics with state-of-the-art WS steganalysis. Empirical results from large datasets indicate significant increases in detection performance, in particular for small payloads. This specific weakness of color covers calls into question the common assumption that grayscale image steganography generalizes to color images by treating each chroma channel independently.

This paper proposes a forensic technique to localize duplicated image regions based on Zernike moments of small image blocks. We exploit rotation invariance properties to reliably unveil duplicated regions after arbitrary rotations. We devise a novel block matching procedure based on locality sensitive hashing and reduce false positives by examining the moments' phase. A massive experimental test setup benchmarks our algorithm against state-of-the-art methods under various perspectives, examining both pixel-level localization and image-level detection performance. By taking signal characteristics into account and distinguishing between “textured” and “smooth” duplicated regions, we find that the proposed method outperforms prior art in particular when duplicated regions are smooth. Experiments indicate high robustness against JPEG compression, blurring, additive white Gaussian noise, and moderate scaling.

Resampling detection has become a standard tool for forensic analyses of digital images. This paper presents new variants of image transformation operations which are undetectable by resampling detectors based on periodic variations in the residual signal of local linear predictors in the spatial domain. The effectiveness of the proposed method is supported with evidence from experiments on a large image database for various parameter settings. We benchmark detectability as well as the resulting image quality against conventional linear and bicubic interpolation and interpolation with a sinc kernel. These early findings on ldquocounter-forensicrdquo techniques put into question the reliability of known forensic tools against smart counterfeiters in general, and might serve as benchmarks and motivation for the development of much improved forensic techniques.

Compared to the prominent role digital images play in nowadays multimedia society, research in the field of image authenticity is still in its infancy. Only recently, research on digital image forensics has gained attention by addressing tamper detection and image source identification. However, most publications in this emerging field still lack rigorous discussions of robustness against strategic counterfeiters, who anticipate the existence of forensic techniques. As a result, the question of trustworthiness of digital image forensics arises. This work will take a closer look at two state-of-the-art forensic methods and proposes two counter-techniques; one to perform resampling operations undetectably and another one to forge traces of image origin. Implications for future image forensic systems will be discussed.