Image forgery detection confronts image composition

Schetinger, Victor; Iuliani, Massimo; Piva, Alessandro; Oliveira, Manuel M.

doi:10.1016/j.cag.2017.08.014

Cited by 16 publications

(7 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, the method proposed in this paper is suitable for detecting image tampering under lossy compression, but it is not ideal for detecting tampering under low quality or lossless compression. Second, as the detection of image forgery and image composition is in a constant arms-race [31], the advanced technology behind DeepFake will continue to develop. Therefore, we will continue to evaluate and improve the robustness of our detection method.…”

Section: Discussionmentioning

confidence: 99%

A Novel Counterfeit Feature Extraction Technique for Exposing Face-Swap Images Based on Deep Learning and Error Level Analysis

Zhang

Zhao

2020

Entropy

View full text Add to dashboard Cite

The quality and efficiency of generating face-swap images have been markedly strengthened by deep learning. For instance, the face-swap manipulations by DeepFake are so real that it is tricky to distinguish authenticity through automatic or manual detection. To augment the efficiency of distinguishing face-swap images generated by DeepFake from real facial ones, a novel counterfeit feature extraction technique was developed based on deep learning and error level analysis (ELA). It is related to entropy and information theory such as cross-entropy loss function in the final softmax layer. The DeepFake algorithm is only able to generate limited resolutions. Therefore, this algorithm results in two different image compression ratios between the fake face area as the foreground and the original area as the background, which would leave distinctive counterfeit traces. Through the ELA method, we can detect whether there are different image compression ratios. Convolution neural network (CNN), one of the representative technologies of deep learning, can extract the counterfeit feature and detect whether images are fake. Experiments show that the training efficiency of the CNN model can be significantly improved by the ELA method. In addition, the proposed technique can accurately extract the counterfeit feature, and therefore achieves outperformance in simplicity and efficiency compared with direct detection methods. Specifically, without loss of accuracy, the amount of computation can be significantly reduced (where the required floating-point computing power is reduced by more than 90%).

show abstract

Section: Discussionmentioning

confidence: 99%

A Novel Counterfeit Feature Extraction Technique for Exposing Face-Swap Images Based on Deep Learning and Error Level Analysis

Zhang

Zhao

2020

Entropy

View full text Add to dashboard Cite

show abstract

“…The proposed forgery detection method is suitable for detecting forgery images from number of faces. Schetinger et al [13] offered a platform to inhale the forensic scenario in the fields of composition and digital image forensics. The benefit was that they were tuned properly for the specific case, but lacked the theoretical structure.…”

Section: Learning-based Techniquesmentioning

confidence: 99%

“…The operation copy-paste is same as splicing, but the portion of the image is transferred within the image. The process of retouching cannot be defined clearly but is something similar to that of blurring the portion of the image, recolouring, and applying filters [12,13]. The image forgery is carried out in any of the following ways.…”

Section: Introductionmentioning

confidence: 99%

Illumination‐based texture descriptor and fruitfly support vector neural network for image forgery detection in face images

Cristin¹,

Ananth²,

Raj

2018

IET Image Processing

View full text Add to dashboard Cite

“…Automatic methods able to detect forgeries in digital images are fundamental to counter the ever-increasing production and spread of fake imagery through the media. Image forensic methods [1,2,3,4,5,6,7] try to solve this problem by observing distinctive traces left by manipulation operations. Depending on the exploited evidences, forensic methods can be broadly classied into signalbased and scene-based.…”

Section: Introductionmentioning

confidence: 99%

A vision-based fully automated approach to robust image cropping detection

Fanfani

Iuliani

Bellavia

et al. 2020

Signal Processing: Image Communication

Self Cite

View full text Add to dashboard Cite

The denition of valid and robust methodologies for assessing the authenticity of digital information is nowadays critical to contrast social manipulation through the media. A key research topic in multimedia forensics is the development of methods for detecting tampered content in large image collections without any human intervention. This paper introduces AMARCORD (Automatic Manhattan-scene AsymmetRically CrOpped imageRy Detector), a fully automated detector for exposing evidences of asymmetrical image cropping on Manhattan-World scenes. The proposed solution estimates and exploits the camera principal point, i.e., a physical feature extracted directly from the image content that is quite insensitive to image processing operations, such as compression and resizing, typical of social media platforms. Robust computer vision techniques are employed throughout, so as to cope with large sources of noise in the data and improve detection performance. The method leverages a novel metric based on robust statistics, and is also capable to decide autonomously whether the image at hand is tractable or not. The results of an extensive experimental evaluation covering several cropping scenarios demonstrate the eectiveness and robustness of our approach.

show abstract

Image forgery detection confronts image composition

Cited by 16 publications

References 68 publications

A Novel Counterfeit Feature Extraction Technique for Exposing Face-Swap Images Based on Deep Learning and Error Level Analysis

A Novel Counterfeit Feature Extraction Technique for Exposing Face-Swap Images Based on Deep Learning and Error Level Analysis

Illumination‐based texture descriptor and fruitfly support vector neural network for image forgery detection in face images

A vision-based fully automated approach to robust image cropping detection

Contact Info

Product

Resources

About