An improved anti-forensics JPEG compression using Least Cuckoo Search algorithm

Shelke, Priya; Prasad, Jayashree R.

doi:10.1080/13682199.2017.1389832

Cited by 20 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed method was evaluated and the results showed that it can fool some of the state-of-the-art image forensics tools. Shelke and Prasad [90] proposed a Least Cuckoo search algorithm to remove detectable traces left by JPEG compression in both the spatial and transform domains. The authors devised a new fitness function, called histogram deviation, and used it for optimisation.…”

Section: Afts For Jpeg Blocking Artefacts Removalmentioning

confidence: 99%

“…analyse relationships of DWT coefficients across different decomposition levels, apply Hough transform to joint DWT histogram to derive features for SVM, AUC = 0.97 Fahmi and Würtz [127] 2016 quantisation own dataset of 280 images, QF ∈ [30,90] noise dithering is measured by spatial frequency phase variations in tampered image blocks, highest accuracy = 93 at QF = 30 and 70% for QF = 30 and 95 Barni et al [128] 2016 double JPEG compression RAISE dataset [129] (1400 images for training, 300 for kernel settings, 300 for testing, size 4288 ×2848 and 2144×1424, QF ∈ [49,87]) adversary-aware AAFT for double JPEG compression based on data-driven approaches and adversary-aware SVM, efficiently counter universal anti-forensic attacks Zeng et al [130] 2018 quantisation 1338 greyscale images from UCID [78] compression for the case when the anti-forensic operation is applied to hide the traces of tampering. The algorithm is also able to counter CE and median filtering anti-forensics, as well as detecting various image processing operations like scaling, rotation, filtering (mean filtering, Gaussian filtering, Weiner filtering) and proved to be used as a multipurpose anti-forensic countering method.…”

Section: Aafts For Compressionmentioning

confidence: 99%

See 1 more Smart Citation

Bibliography of digital image anti‐forensics and anti‐anti‐forensics techniques

Qureshi

El-Alfy

2019

IET Image Processing

View full text Add to dashboard Cite

Section: Afts For Jpeg Blocking Artefacts Removalmentioning

confidence: 99%

Section: Aafts For Compressionmentioning

confidence: 99%

Bibliography of digital image anti‐forensics and anti‐anti‐forensics techniques

Qureshi

El-Alfy

2019

IET Image Processing

View full text Add to dashboard Cite

“…However, the technique failed to manage huge datasets, creating several issues. Several optimization methods (Ratre & Pankajakshan, 2017 ;Dhumane & Prasad, 2017 ;Nipanikar, et al, 2017 ;Shelke & Prasad, 2018 ;Krishnamoorthy & Asokan, 2014) are utilized for privacy preservation to optimize the results.…”

Section: Introductionmentioning

confidence: 99%

A Technique for Securing Big Data Using K-Anonymization With a Hybrid Optimization Algorithm

Madan¹,

Goswami

2021

International Journal of Operations Research and Information Systems

View full text Add to dashboard Cite

The recent techniques built on cloud computing for data processing is scalable and secure, which increasingly attracts the infrastructure to support big data applications. This paper proposes an effective anonymization based privacy preservation model using k-anonymization criteria and Grey wolf-Cat Swarm Optimization (GWCSO) for attaining privacy preservation in big data. The anonymization technique is processed by adapting k- anonymization criteria for duplicating k records from the original database. The proposed GWCSO is developed by integrating Grey Wolf Optimizer (GWO) and Cat Swarm Optimization (CSO) for constructing the k-anonymized database, which reveals only the essential details to the end users by hiding the confidential information. The experimental results of the proposed technique are compared with various existing techniques based on the performance metrics, such as Classification accuracy (CA) and Information loss (IL). The experimental results show that the proposed technique attains an improved CA value of 0.005 and IL value of 0.798, respectively.

show abstract

“…The bat optimization algorithm is modified in (Kaur et al , 2017) for segmenting the brain tumor images. The optimization techniques (Dhumane and Prasad, 2017; Nipanikar et al , 2017; Shelke and Prasad, 2018; Bhopale et al , 2014) have applications in brain tumor segmentation. Also, literature has used the semiautomatic brain tumor segmentation (Sauwen et al , 2017) approaches.…”

Section: Introductionmentioning

confidence: 99%

Hybrid active contour model and deep belief network based approach for brain tumor segmentation and classification

Raju¹,

Pabboju

Rao

2019

View full text Add to dashboard Cite

Purpose Brain tumor segmentation and classification is the interesting area for differentiating the tumorous and the non-tumorous cells in the brain and classifies the tumorous cells for identifying its level. The methods developed so far lack the automatic classification, consuming considerable time for the classification. In this work, a novel brain tumor classification approach, namely, harmony cuckoo search-based deep belief network (HCS-DBN) has been proposed. Here, the images present in the database are segmented based on the newly developed hybrid active contour (HAC) segmentation model, which is the integration of the Bayesian fuzzy clustering (BFC) and the active contour model. The proposed HCS-DBN algorithm is trained with the features obtained from the segmented images. Finally, the classifier provides the information about the tumor class in each slice available in the database. Experimentation of the proposed HAC and the HCS-DBN algorithm is done using the MRI image available in the BRATS database, and results are observed. The simulation results prove that the proposed HAC and the HCS-DBN algorithm have an overall better performance with the values of 0.945, 0.9695 and 0.99348 for accuracy, sensitivity and specificity, respectively. Design/methodology/approach The proposed HAC segmentation approach integrates the properties of the AC model and BFC. Initially, the brain image with different modalities is subjected to segmentation with the BFC and AC models. Then, the Laplacian correction is applied to fuse the segmented outputs from each model. Finally, the proposed HAC segmentation provides the error-free segments of the brain tumor regions prevailing in the MRI image. The next step is to extract the useful features, based on scattering transform, wavelet transform and local Gabor binary pattern, from the segmented brain image. Finally, the extracted features from each segment are provided to the DBN for the training, and the HCS algorithm chooses the optimal weights for DBN training. Findings The experimentation of the proposed HAC with the HCS-DBN algorithm is analyzed with the standard BRATS database, and its performance is evaluated based on metrics such as accuracy, sensitivity and specificity. The simulation results of the proposed HAC with the HCS-DBN algorithm are compared against existing works such as k-NN, NN, multi-SVM and multi-SVNN. The results achieved by the proposed HAC with the HCS-DBN algorithm are eventually higher than the existing works with the values of 0.945, 0.9695 and 0.99348 for accuracy, sensitivity and specificity, respectively. Originality/value This work presents the brain tumor segmentation and the classification scheme by introducing the HAC-based segmentation model. The proposed HAC model combines the BFC and the active contour model through a fusion process, using the Laplacian correction probability for segmenting the slices in the database.

show abstract

An improved anti-forensics JPEG compression using Least Cuckoo Search algorithm

Cited by 20 publications

References 15 publications

Bibliography of digital image anti‐forensics and anti‐anti‐forensics techniques

Bibliography of digital image anti‐forensics and anti‐anti‐forensics techniques

A Technique for Securing Big Data Using K-Anonymization With a Hybrid Optimization Algorithm

Hybrid active contour model and deep belief network based approach for brain tumor segmentation and classification

Contact Info

Product

Resources

About