Robust Estimation of Upscaling Factor on Double JPEG Compressed Images

Lu, Wei; Zhang, Qin; Luo, Shangjun; Zhou, Yicong; Huang, Jiwu; Shi, Yun-Qing

doi:10.1109/tcyb.2021.3069999

Cited by 8 publications

(3 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the foundation of single operation detection, a few researchers transfer their attention on detection multiple operations (so-called operation chain [5]), which is close to realistic scenario and a big challenge. Several operation chains consisting of some specific operations have been studied, e.g., double JPEG interleaved by contrast enhancement [6], double JPEG interleaved by resampling [7], [8], [9], JPEG followed by linear filter [10], etc. Similar to the single operation detection, the operation chain detection need to design a extractor of the unique forensics feature based on modeling the manipulated signal and feed the feature to train the classifier.…”

Section: Introductionmentioning

confidence: 99%

The Forensicability of Operation Detection in Image Operation Chain

2022

View full text Add to dashboard Cite

A large number of forensics research focus on operation detection to reveal the evidence of forgery action in the digital image. In the early works, analyst firstly model the probability distribution of single operation, and design the forensic tools based on feature extraction and machine learning based classifier. With increasing dimension of the feature and facing multiple operations detection scenario, the physical meaning of the feature gradually become ambiguous. Especially, since deep learning algorithm was used in forensic research, the automatic feature selection and making decision with high performance of classification conceals the intrinsic forensic clues. In this paper, we explore the availability of feature for operation detection in the operation chain, so called forensicability. An anti-forensic attack algorithm is introduced to formulate the impact on the feature due to the following operation. We propose two measurements: attack angle and scale, mutual information scale to indicate the forensic feature variation after the image manipulated by the following operation. The uncoupled relationship can be revealed by our methods. In the experiments, four operation chains involving ten operations are considered as the case study. The results are encouraging and improve the explanation of the forensics method based on high dimensional features.INDEX TERMS Forensicability, Image operation chain detection, Image forensics.

show abstract

Section: Introductionmentioning

confidence: 99%

The Forensicability of Operation Detection in Image Operation Chain

2022

View full text Add to dashboard Cite

show abstract

“…10 Some works have been proposed for forgery detection. 2,[11][12][13][14][15][16][17][18][19] Chen et al 16 detect median filtering by Convolutional Neural Networks (CNNs). Feng et al 17 utilized the normalized energy density in the frequency domain to detect resampled image.…”

Section: Introductionmentioning

confidence: 99%

“…The purpose of forgery detection is to discriminate whether a given image is pristine or forged which provides image‐level analysis 10 . Some works have been proposed for forgery detection 2,11–19 . Chen et al 16 detect median filtering by Convolutional Neural Networks (CNNs).…”

Section: Introductionmentioning

confidence: 99%

Document images forgery localization using a two‐stream network

Liu

Zhu

et al. 2021

Int J of Intelligent Sys

Self Cite

View full text Add to dashboard Cite

Document images often contain essential and sensitive information. With image editing software, one can easily manipulate the semantic meaning of the document image by copy-move, splicing, and removal, which causes many security issues. Hence, the document image forgery detection and localization are of great significance. In this paper, a novel two-stream network is proposed to detect and locate the forgery regions of document images. One stream captures forgery traces from the spatial information, including unnatural boundaries, contrast/brightness inconsistencies, and blurring. The other stream eliminates the image semantics by six residual filters, then capture the anomalous features between neighboring pixels introduced by upsampling, downsamping, and inpainting. Finally, the discriminant network is introduced to deeply fuse features from the two streams, and discriminates whether each image patch is forged or not using global average pooling and fully connected layer. Extensive experimental results on our constructed document image data set and the Security AI Challenger Program data set demonstrate the proposed two-stream network outperforms state-of-the-art methods. This proposed two-stream network is also better than each single stream, and is robust to some common forgery postprocessing operations.

show abstract