Comprint: Image Forgery Detection and Localization Using Compression Fingerprints

Mareen, Hannes; Bussche, Dante Vanden; Fabrizio, Guillaro,; Cozzolino, Davide; Wallendael, Glenn Van; Lambert, Peter; Verdoliva, Luisa

doi:10.1007/978-3-031-37742-6_23

Cited by 6 publications

(11 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The effectiveness of the proposed counter-forensic approaches is evaluated through extensive experimental analysis on attacking two noiseprint-based forensics methods. The first is the original noiseprint method ( Cozzolino & Verdoliva, 2020 ) which denoted as OrgNoiseprint , and the other is the method proposed in Mareen et al (2022) which denoted as Comprint . The OrgNoiseprint method utilizes the noiseprint only in the forensic tasks, while the Comprint method blends the noiseprint with the compression fingerprints to boost the performance of the forensic tasks.…”

Section: Experimental Analysismentioning

confidence: 99%

“…This makes the noiseprint an ideal tool for several forensic applications as proposed in Cozzolino Giovanni Poggi Luisa Verdoliva (2019) , Marra et al (2020) and Cozzolino et al (2020) . Additionally, the noiseprint becomes an essential building block in many advanced recent forensics algorithms ( Mareen et al, 2022 ; Marra et al, 2020 ) that blend the noiseprint with other fingerprints (or features from other domains) to achieve superior performance in different forensics tasks. Thus, we can treat the noiseprint as a cornerstone in a family of related algorithms that handle different forensics tasks.…”

Section: Introductionmentioning

confidence: 99%

“…Additionally, we evaluated the effectiveness of the proposed approaches against two common forensic tasks, which are the forgery localization and camera source identification tasks. The proposed approaches are able to significantly reduce several forensic accuracy scores compared with two noiseprint-based forensics methods ( Cozzolino & Verdoliva, 2020 ; Mareen et al, 2022 ) while at the same time producing high-fidelity images.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Neural noiseprint transfer: a generic noiseprint-based counter forensics framework

Elliethy

2023

PeerJ Computer Science

View full text Add to dashboard Cite

A noiseprint is a camera-related artifact that can be extracted from an image to serve as a powerful tool for several forensic tasks. The noiseprint is built with a deep learning data-driven approach that is trained to produce unique noise residuals with clear traces of camera-related artifacts. This data-driven approach results in a complex relationship that governs the noiseprint with the input image, making it challenging to attack. This article proposes a novel neural noiseprint transfer framework for noiseprint-based counter forensics. Given an authentic image and a forged image, the proposed framework synthesizes a newly generated image that is visually imperceptible to the forged image, but its noiseprint is very close to the noiseprint of the authentic one, to make it appear as if it is authentic and thus renders the noiseprint-based forensics ineffective. Based on deep content and noiseprint representations of the forged and authentic images, we implement the proposed framework in two different approaches. The first is an optimization-based approach that synthesizes the generated image by minimizing the difference between its content representation with the content representation of the forged image while, at the same time, minimizing the noiseprint representation difference from the authentic one. The second approach is a noiseprint injection-based approach, which first trains a novel neural noiseprint-injector network that can inject the noiseprint of an image into another one. Then, the trained noiseprint-injector is used to inject the noiseprint from the authentic image into the forged one to produce the generated image. The proposed approaches are generic and do not require training for specific images or camera models. Both approaches are evaluated on several datasets against two common forensic tasks: the forgery localization and camera source identification tasks. In the two tasks, the proposed approaches are able to significantly reduce several forensic accuracy scores compared with two noiseprint-based forensics methods while at the same time producing high-fidelity images. On the DSO-1 dataset, the reduction in the forensic accuracy scores has an average of 75%, while the produced images have an average PSNR of 31.5 dB and SSIM of 0.9. The source code of the proposed approaches is available on GitHub (https://github.com/ahmed-elliethy/nnt).

show abstract

Section: Experimental Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Neural noiseprint transfer: a generic noiseprint-based counter forensics framework

Elliethy

2023

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…A recent, promising method is Comprint [4], which utilizes compression fingerprints to detect forgeries in images. The underlying assumption is that the forged area underwent different compression than the real area, thus generating another compression fingerprint.…”

Section: Introductionmentioning

confidence: 99%

Training Data Improvement for Image Forgery Detection using Comprint

Mareen

Bussche

Wallendael

et al. 2023

2023 IEEE International Conference on Consumer Electronics (ICCE)

Self Cite

View full text Add to dashboard Cite

Manipulated images are a threat to consumers worldwide, when they are used to spread disinformation. Therefore, Comprint enables forgery detection by utilizing JPEGcompression fingerprints. This paper evaluates the impact of the training set on Comprint's performance. Most interestingly, we found that including images compressed with low quality factors during training does not have a significant effect on the accuracy, whereas incorporating recompression boosts the robustness. As such, consumers can use Comprint on their smartphones to verify the authenticity of images.

show abstract

“…Existing fusion methods that combine image forgery detection methods typically have some limitations [6][7][8][9][10][11][12]. First, they may not provide generic frameworks to easily add existing forgery detection methods.…”

Section: Introductionmentioning

confidence: 99%

Harmonizing Image Forgery Detection & Localization: Fusion of Complementary Approaches

Mareen,

De Neve,

Lambert

et al. 2023

J. Imaging

View full text Add to dashboard Cite

Image manipulation is easier than ever, often facilitated using accessible AI-based tools. This poses significant risks when used to disseminate disinformation, false evidence, or fraud, which highlights the need for image forgery detection and localization methods to combat this issue. While some recent detection methods demonstrate good performance, there is still a significant gap to be closed to consistently and accurately detect image manipulations in the wild. This paper aims to enhance forgery detection and localization by combining existing detection methods that complement each other. First, we analyze these methods’ complementarity, with an objective measurement of complementariness, and calculation of a target performance value using a theoretical oracle fusion. Then, we propose a novel fusion method that combines the existing methods’ outputs. The proposed fusion method is trained using a Generative Adversarial Network architecture. Our experiments demonstrate improved detection and localization performance on a variety of datasets. Although our fusion method is hindered by a lack of generalization, this is a common problem in supervised learning, and hence a motivation for future work. In conclusion, this work deepens our understanding of forgery detection methods’ complementariness and how to harmonize them. As such, we contribute to better protection against image manipulations and the battle against disinformation.

show abstract

Comprint: Image Forgery Detection and Localization Using Compression Fingerprints

Cited by 6 publications

References 29 publications

Neural noiseprint transfer: a generic noiseprint-based counter forensics framework

Neural noiseprint transfer: a generic noiseprint-based counter forensics framework

Training Data Improvement for Image Forgery Detection using Comprint

Harmonizing Image Forgery Detection & Localization: Fusion of Complementary Approaches

Contact Info

Product

Resources

About