CoChat

The DOI matches its Crossref record; 56 of the 56 references it cites were found in a registry or an index; 1 of the 7 sources its claims cite were checked for support.

A Faster and Robust Artificial Neural Network Based Image Encryption Technique With Improved SSIM

Open access

Abstract

A robust image encryption process is still one of the most challenging tasks in image security owing to massive degree and sensitivity nature of information in the form of pixels. The hurdles include greater computational difficulty, information loss during encryption, universality, applicability of the approach, and less scalability. Many image encryption methods existing in literature merely encrypt a portion of the data. Therefore, we propose a robust, dynamic, and sophisticated technique to enhance the encryption process to make it difficult for an attacker to gain unauthorized access to the pixel data. The proposed system uses a novel analytical research methodology through dynamically harnessing the potential of neural network that offers better forward and backward secrecy, dynamic control, and automatic management unlike any existing system. The encryption procedure comprises of two levels, first level is confusion- permutation of input image and second level is diffusion by Bit XOR operation for secure transmission and storage of images. Finally, the encrypted image is used as a target for training the Artificial Neural Network (ANN) model. ANN trained values are used for final level of encryption to develop a Neural Network (NN)-based cryptosystem, where the crypto analyst or the cracker need to know the number of adaptive iterations and the final weights for the encryption and decryption systems to crack the system which offers higher degree of resiliency towards potential threats. Results and security analysis show that our algorithm has good encryption effect, ability of resisting exhaustive attack, statistical attack, and differential attack. The system performance after implementing the proposed method is compared with existing methods present in literature with respect to processing time and Structural Similarity Index Measure (SSIM). Our proposed method offers significant reduction in encryption time and is approximately 10-15% faster than others with SSIM of 0.002165, close to zero after encryption. It also successfully balances the image quality with higher image security and lower computational complexity.

Overview

CoChat Summary

TL;DR

The paper proposes a two-level image encryption scheme combining permutation and Bit XOR diffusion with an ANN trained on the encrypted image to add a neural-network-based final encryption layer. It reports faster processing than several baselines and security metrics including key space \(2^{136}\), NPCR 99.75%, UACI 33.61%, entropy 7.9846, and SSIM 0.002165 after encryption.

Key findings

  • The proposed scheme reports NPCR 99.75%, UACI 33.61%, correlation coefficients of -0.006508 (horizontal), 0.022328 (vertical), and 0.015374 (diagonal), and entropy 7.9846 in Table VI.
  • Key space is stated as \(2^{136}\), and the encrypted “Lena” image passed all 6 NIST SP800-6 tests, with p-values such as approximate entropy 0.8673, cumulative sums forward 0.8427, cumulative sums reverse 0.7240, FFT 0.9818, rank 0.6224, and frequency 0.6287.
  • Table VIII lists proposed processing time as 32 s versus Wang et al. 39 s, Dridi et al. 46 s, and Chen et al. 51 s; the abstract states the method is approximately 10–15% faster than others.
  • The abstract reports SSIM of 0.002165 after encryption, and Table IX reports SSIM(a) values of 0.0021 for Lena, 0.010 for Baboon, 0.0086 for Peppers, and 0.0063 for Dog, with SSIM(b) = 1.000 for all listed test images.

Methods

  • Design: three sequential algorithms perform Level-1 confusion-permutation using the input image and transmitter secret key with Mersenne Twister, Level-2 diffusion via Bit XOR/encoding, then ANN training with a [0:255] pixel array as input and the encrypted image as target; ANN-trained values are used for final encryption. The ANN is described as 256 input neurons, a single hidden layer of 256 neurons, and 256 output neurons, using tan sigmoid and pure linear activation functions, Levenberg-Marquardt training, and 12 epochs.
  • Data: experiments use the USC-SIPI Weber dataset with 28 monochrome and 16 color images ranging from 256×256 to 1024×1024, plus McGill 2018 high-definition color images of 1920×2560 pixels; color images are converted to grayscale, with emphasis on real-time color images.
  • Analysis: MATLAB Neural Network Toolbox 2019a is used; evaluation includes MSE, PSNR, SSIM, chi-square, correlation, NPCR, UACI, entropy, key space, NIST SP800-6 randomness tests, and crop/noise attack analysis.

Limitations

  • The paper does not state a limitations section.
  • Evident from the text: the ANN architecture is described inconsistently, first as “a single hidden layer of 256 neurons” and later as “a multi-layer perceptron of ANN with 255 hidden layers.”
  • Evident from the text: Table VIII reports proposed SSIM 0.002165, while compared methods have lower SSIM values (0.000106, 0.000112, 0.000021), which complicates the claim of improved SSIM; the algorithm pseudocode is also incomplete/garbled.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1109/access.2024.3353294

Cites

56 of 56 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Verification

Claims the paper makes

0 Valid · 3 Not valid · 4 Not checked · 50 Own results and interpretations

23 more claims

Create a free account to see all 57 claims and every source verdict.

See all claims — free account
  • It may state two separate claims as one. 16
  • Probably not a substantial claim. 9
  • The quote only partly states this claim. 4

Create a free account to see these claims.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

3 of 3

Cited works that were retracted

Works this paper cites that were later retracted, from the retraction notices publishers deposit. Major when the notice came out before this paper was published.

1 of 1

Citations

Cites

1 retracted

Show all 54 references

Research works printed but not linked: 2

  1. Bharadi, 2018, Cloud based NoSQL database for Iris based biometric system Azure based Cosmos DB implementation, 7, 397
  2. Weber, 2018, The USC-SIPI Image Database. 2014

Metadata

Authors
Panigrahy, A. K., Maniyath, S. R., Sathiyanarayanan, M., Dholvan, M., Ramaswamy, T., Hanumanthakari, S., Vignesh, N. A., Kanithan, S., & Swain, R.
Affiliations
  • ICFAI Foundation for Higher Education (IN)
  • MVJ College of Engineering (IN)
  • Research & Innovation Centre, MIT Square, London, U.K.
  • Department of ECE, Sreenidhi Institute of Science and Technology, Hyderabad, Telangana, India
  • Department of ECE, Gokaraju Rangaraju Institute of Engineering and Technology (GRIET), Hyderabad, Telangana, India
  • Jain University (IN)
  • Parala Maharaja Engineering College (IN)
Venue
IEEE Access
Published
2024
Volume
12
Pages
10818-10833
ISSN
2169-3536 (ISSN-L)
OpenAlex
W4390816738
Cited by
42
References
54
Citations by year
2026: 18 · 2025: 18 · 2024: 6
FWCI
4.56
Type
journal article
Language
en
Open access
Locations
  • IEEE Access (publishedVersion, cc-by-nc-nd)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • ICFAI Foundation for Higher Education Hyderabad (IcfaiTech), Hyderabad, India
  • MATLAB tool for conduction of the research work
  • MIT Square and Raj Square Charity Foundation, Department of Computer Science, University of Beira Interior, Covilhã, Portugal
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Chaos-based Image/Signal Encryption
  • Physical Sciences › Computer Science › Artificial Intelligence › Computer Science and Engineering
  • Physical Sciences › Computer Science › Artificial Intelligence › Cryptographic Implementations and Security
Keywords
image encryption, structural similarity index, encryption speed, differential attack resistance, statistical attack resistance

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

The claim verdicts this report counts are experimental: their accuracy is not yet measured.

A language model drew the claims from the paper on 2026-10-21, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-21 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: A Faster and Robust Artificial Neural Network Based Image Encryption Technique With Improved SSIM. https://app.cochat.ai/papers/10.1109/access.2024.3353294
The paper
Panigrahy, A. K., Maniyath, S. R., Sathiyanarayanan, M., Dholvan, M., Ramaswamy, T., Hanumanthakari, S., Vignesh, N. A., Kanithan, S., & Swain, R. (2024). A Faster and Robust Artificial Neural Network Based Image Encryption Technique With Improved SSIM. IEEE Access. https://doi.org/10.1109/access.2024.3353294

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.