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 accessAbstract
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
Cites
Statistics
Verification
Claims the paper makes
0 Valid · 3 Not valid · 4 Not checked · 50 Own results and interpretations
In the paper
“However, its SSIM is better than that of Wang et.al. [54].”
§ A Faster and Robust Artificial Neural Network based Image Encryption Technique with Improved SSIM ‡ > H. STATISTICAL RANDOMNESS ANALYSIS
What the sources say
- Not checked — no full text of the sourcecites [54] source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Lena 0.0021 1.000 Baboon 0.010 1.000 Peppers 0.0086 1.000 Dog 0.0063 1.000”
§ A Faster and Robust Artificial Neural Network based Image Encryption Technique with Improved SSIM ‡ > H. STATISTICAL RANDOMNESS ANALYSIS
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It can be seen from the table that the generated cipher image passed all 6 tests, which shows that the sequence generated by our algorithm is random.”
§ A Faster and Robust Artificial Neural Network based Image Encryption Technique with Improved SSIM ‡ > H. STATISTICAL RANDOMNESS ANALYSIS
plainSingle case- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It is clear from the pattern of the numerical results presented in Fig. 14 that the processing times of all ANN approaches are essentially the same.”
§ A Faster and Robust Artificial Neural Network based Image Encryption Technique with Improved SSIM ‡ > H. STATISTICAL RANDOMNESS ANALYSIS
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Results and security analysis show that our algorithm has good encryption effect, ability of resisting exhaustive attack, statistical attack, and differential attack.”
- Also stated in: § B. ALGORITHM FOR NURAL NETWORK GENERATION · boosted
“The experimental findings demonstrate that the proposed approach produces good, encrypted outcomes and can withstand all types of statistical and differential attacks since the pixel values have been altered.”
§ A Faster and Robust Artificial Neural Network based Image Encryption Technique with Improved SSIM ‡ > Abstract
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § B. ALGORITHM FOR NURAL NETWORK GENERATION · boosted
23 more claims
Create a free account to see all 57 claims and every source verdict.
- It may state two separate claims as one. 16
- Probably not a substantial claim. 9
- The quote only partly states this claim. 4
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“However, by increasing computational complexity, AI’s ability to protect images depends on the size and quality of training datasets21,22.”
From Image adaptive encryption using EfficientNet B3 feature guided multi scroll chaotic map with modulo controlled pseudo parallel processing (2025) · cites this paper as [22]
Experimental — accuracy not yet measured
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.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ A Faster and Robust Artificial Neural Network based Image Encryption Technique with Improved SSIM ‡ > C. VISUAL OUTCOME ANALYSIS
“The six sample images from the USC SIPI Image Database are highlighted in Table II.”
§ A Faster and Robust Artificial Neural Network based Image Encryption Technique with Improved SSIM ‡ > C. VISUAL OUTCOME ANALYSIS
“TABLE II STAGES OF VISUAL OUTCOMES OF PROPOSED SYSTEM Sample 1 Sample 2 Sample 3 Sample 4”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ A Faster and Robust Artificial Neural Network based Image Encryption Technique with Improved SSIM ‡ > B. ANALYSIS STRATEGY
“The number of epochs (12 iterations) is shown by the X-axis.The MSE that occurred for each iteration is shown on the Y-axis.”
§ A Faster and Robust Artificial Neural Network based Image Encryption Technique with Improved SSIM ‡ > B. ANALYSIS STRATEGY
“The histogram inaccuracy graph is depicted in Fig. 9.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ A Faster and Robust Artificial Neural Network based Image Encryption Technique with Improved SSIM ‡ > B. ALGORITHM FOR NURAL NETWORK GENERATION
“an ANN Model of 256 neurons as input layer, a single hidden layer of 256 neurons and an output layer of 256 neurons”
§ A Faster and Robust Artificial Neural Network based Image Encryption Technique with Improved SSIM ‡ > B. ANALYSIS STRATEGY
“A multi-layer perceptron of ANN with 255 hidden layers and a single input/output layer is used in the suggested system.”
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.
A note, not an issue: for example, a cited work that was retracted only after this paper was published, which its authors could not have known.
In the paper
“10.1109/ICSCSE.2016.0147”
Cited work 10.1109/icscse.2016.0147 · retraction date not known · this paper published 2024
Citations
Cites
1 retracted
Retracted: The Color Image Encryption Technology Based on DNA Encoding & Sine Chaos
Awdun, B., & Li, G. (2016) · International Conference on Smart City and Systems Engineering · doi:10.1109/icscse.2016.0147 · Cited by 15
RetractedA new chaos-based fast image encryption algorithm
Wang, Y., Wong, K.-W., Liao, X., & Chen, G. (2011) · Applied Soft Computing · doi:10.1016/j.asoc.2009.12.011 · Cited by 561
Secure Medical Data Transmission Model for IoT-Based Healthcare Systems
Elhoseny, M., Ramirez-Gonzalez, G., Abu-Elnasr, O. M., Shawkat, S. A., Arunkumar, N., & Farouk, A. (2018) · IEEE Access · doi:10.1109/access.2018.2817615 · Cited by 546
A novel color image encryption algorithm based on DNA sequence operation and hyper-chaotic system
Wei, X., Guo, L., Zhang, Q., Zhang, J., & Lian, S. (2012) · Journal of Systems and Software · doi:10.1016/j.jss.2011.08.017 · Cited by 389
Reversible Data Hiding in Encrypted Images With Distributed Source Encoding
Qian, Z., & Zhang, X. (2016) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2015.2418611 · Cited by 313
Chen, W.-H., Luo, S., & Zheng, W. X. (2016) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2015.2512849 · Cited by 280
Depreciating motivation and empirical security analysis of chaos-based image and video encryption
Preishuber, M., Hutter, T., Katzenbeisser, S., & Uhl, A. (2018) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2018.2812080 · Cited by 256
Encryption-Then-Compression Systems Using Grayscale-Based Image Encryption for JPEG Images
Chuman, T., Sirichotedumrong, W., & Kiya, H. (2019) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2018.2881677 · Cited by 252
Cryptanalyzing an Image-Scrambling Encryption Algorithm of Pixel Bits
Li, C., Lin, D., & Lu, J. (2017) · IEEE MultiMedia · doi:10.1109/mmul.2017.3051512 · Cited by 218
A novel colour image encryption scheme using rectangular transform-enhanced chaotic tent maps
Wu, X., Zhu, B., Hu, Y., & Ran, Y. (2017) · IEEE Access · doi:10.1109/access.2017.2692043 · Cited by 207
Research works printed but not linked: 2
- Bharadi, 2018, Cloud based NoSQL database for Iris based biometric system Azure based Cosmos DB implementation, 7, 397
- Weber, 2018, The USC-SIPI Image Database. 2014
Cited by
Comprehensive Review and Analysis of Image Encryption Techniques
Mahalakshmi, K. B., & Nagarajan, S. (2025) · IEEE Access · doi:10.1109/access.2025.3578158 · Cited by 58
Hassan, A., & Zhou, L. (2025) · Chaos Solitons & Fractals · doi:10.1016/j.chaos.2024.115986 · Cited by 37
A robust approach to satellite image encryption using chaotic map and circulant matrices
Kanwal, S., Inam, S., Shah, A. A., Iqbal, H., Bilal, A., Hashmi, M. U., & Sarwar, R. (2024) · Engineering Reports · doi:10.1002/eng2.13010 · Cited by 7
Al-Muhammed, M. J. (2024) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2024.109722 · Cited by 7
Qiu, S., Zhang, P., Li, S., & Hu, B. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103883 · Cited by 5
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)
- ORCID
- 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
- gold
- doi.org
- Licence
- 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.