Digital Forensic Enabled Image Authentication Using Least Significant Bit (LSB) with Tamper Localization Based Hash Function

Das, Ujjal Kumar; Samaddar, Shefalika Ghosh; Keserwani, Pankaj Kumar

doi:10.1007/978-981-10-5523-2_14

Cited by 8 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors in [5] proposed the Least Significant Bit (LSB) techniques benefit for authentication of content of an image. But when the noise has been added in the image, it fails to perceive the image exactly and it is appropriate only for grayscale images.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Copyright Infringement Detection of Multimedia Objects using K-L Transform

Pandey

Pradhan

Singh

et al. 2022

2022 4th International Conference on Energy, Power and Environment (ICEPE)

View full text Add to dashboard Cite

The copyright infringement is a critical issue for original copyright owners of multimedia objects like videos, photographs and graphic designs which are uploaded on various peer-to-peer image sharing systems and websites. Copyright infringement negatively impacts copyright holders' interest by performing some extent of modifications in the original uploaded content. Various frame modification and image processing techniques like frame compression, frame speed manipulation, grayscale conversion, cropping and rotation are used by the copyright violators for modification of the original multimedia content. This paper proposes a perceptual hashing technique using Karhunen-Loeve Transform (K-L Transform) for detecting the copyright violations of the multimedia content, so the work acknowledgement should be provided to the original copyright holders.

show abstract

Section: Related Workmentioning

confidence: 99%

“…1 and 0 is placed for higher and lower intensity respectively. It is mentioned in equation(5). ℎ # = $ %0, , < (, %1, , ≥ (, ∀ k, l ∈ [0, 63] 2…”

mentioning

confidence: 99%

Copyright Infringement Detection of Multimedia Objects using K-L Transform

Pandey

Pradhan

Singh

et al. 2022

2022 4th International Conference on Energy, Power and Environment (ICEPE)

View full text Add to dashboard Cite

show abstract

“…Stego image generation process is implemented by replacing the least significant bits of cover image with the most significant bits of secret information. In (Das, Samaddar, and Keserwani 2018), authors proposed to generate an LSB based hash function for the image authentication process, which can provide good imperceptibility between the original image and stego image with hash bits.…”

Section: Least Significant Bit Steganographymentioning

confidence: 99%

“…In this experiment, we evaluate the robustness when recovering the secret image from the target image. For LSB steganography and spatial domain watermarking, we choose LSB-TLH (Das, Samaddar, and Keserwani 2018). For content adaptive steganography, we choose WOW (Holub and Fridrich 2012), HUGO (Pevnỳ, Filler, and Bas 2010) and S-UNIWARD (Holub, Fridrich, and Denemark 2014).…”

Section: Quantitative Comparative Experimentsmentioning

confidence: 99%

Attention Based Data Hiding with Generative Adversarial Networks

2020

AAAI

View full text Add to dashboard Cite

Recently, the generative adversarial network is the hotspot in research and industrial areas. Its application on data generation is the most common usage. In this paper, we propose the novel end-to-end framework to extend its application to data hiding area. The discriminative model simulates the detection process, which can help us understand the sensitivity of the cover image to semantic changes. The generative model is to generate the target image which is aligned with the original cover image. An attention model is introduced to generate the attention mask. This mask can help to generate a better target image without perturbation of the spotlight. The introduction of cycle discriminative model and inconsistent loss can help to enhance the quality of the generated target image in the iterative training process. The training dataset is mixed with intact images and attacked images. The mix training process can further improve robustness. Through the qualitative, quantitative experiments and analysis, this novel framework shows compelling performance and advantages over the current state-of-the-art methods in data hiding applications.

show abstract