The DOI matches its Crossref record; 53 of the 53 references it cites were found in a registry or an index; 8 of the 68 sources its claims cite were checked for support.
A novel single kernel parallel image encryption scheme based on a chaotic map
Open accessAbstract
The development of communication technologies has increased concerns about data security, increasing the prominence of cryptography. Images are one of the most widely shared data, and chaotic ciphers arouse significant interest from researchers, as traditional ciphers are optimized for text encryption. Chaotic encryption schemes perform well for low-quality images, however, they are not fast enough for real-time encryption of Full Ultra HD images. Hence, a novel cipher to be executed in GPU architectures is proposed, where the encryption procedure consists of a single kernel, making it different from previous chaotic works and also from the AES. This enables our work to achieve a throughput of 130.8 GB/s on a GeForce RTX3070 and 251.6 GB/s on a Tesla V100 GPU, an increase of 37\% compared to the AES, and 43 times higher than the previously high for chaotic ciphers. The cipher's security is also verified regarding multiple forms of attacks.
Overview
CoChat Summary
## TL;DR
The paper proposes a CUDA GPU image encryption scheme that uses a discrete-space chaotic map and a single kernel to perform permutation and diffusion simultaneously. It reports peak throughput of 130.8 GB/s on an RTX 3070 and 251.6 GB/s on a Tesla V100, while claiming resistance to several common cryptanalytic attacks.
## Key findings
- The proposed cipher achieves peak throughput of 130.8 GB/s on a GeForce RTX 3070 and 251.6 GB/s on a Tesla V100.
- The paper reports the RTX 3070 result is 37% faster than AES GPU implementations and 43 times higher than the previously high for chaotic ciphers.
- For throughput on the RTX 3070, the cipher encrypts Full Ultra HD (7680 × 4320 × 3) images in 0.76 ms, with 130.8 GB/s throughput; on the same GPU, SD images reach 109.1 GB/s.
- Security tests reported include statistical, differential, brute-force, chosen-plaintext, noise, and occlusion attacks; examples include NPCR values of 99.57%–99.63%, UACI of 33.36%–33.66%, MSE of 10874–11042, and entropy values around 7.9969–7.9972.
## Methods
- The cipher is a parallel image encryption method implemented in CUDA on GPU hardware, using a single kernel for simultaneous permutation-diffusion.
- It uses an adapted discrete-space chaotic map; the paper says the map avoids quantification and has no transient effects or dynamical degradation, and the chaotic sequences are made image-dependent by applying SHA-256 to the plaintext image.
- Evaluation used grayscale test images of 256 × 256 pixels for security analysis, including Black, Clock, Iris, Lena, and Peppers, and throughput was measured on RTX 3070 and Tesla V100 GPUs.
- Analysis included NIST randomness tests, histogram/Pearson/entropy/correlation metrics, NPCR/UACI/MSE for differential attacks, SSIM/PSNR for chosen-plaintext and noise/occlusion tests, and throughput comparisons with prior work.
## Limitations
- The paper does not state a formal limitation section; this is not stated in the paper.
- Security evaluation is reported on a limited set of images and conditions: the text says tests were conducted using 256 × 256 grayscale images for security validation, which may limit generalization to broader image types and datasets; this is evident from the text.
- The throughput comparison excludes chaotic sequence generation time in the authors’ measurements to make comparisons fair, which means the reported throughput is not a full end-to-end encryption cost; this is evident from the text.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
4 Valid · 4 Not valid · 40 Not checked · 46 Own results and interpretations
Some cited sources support this claim and some don’t — read each source’s verdict below.
In the paper
“the most substantial security threat to chaotic encryption algorithms is the nondependence between the original image and the chaotic values making the cipher prone to chosen plain-text attacks [3, 11, 28].”
What the sources say
- Partly supportedcites [3] 3. Alanazi, A.S., Munir, N., Khan, M., Asif, M., Hussain, I.: Cryptanalysis of novel image encryption scheme based on multiple chaotic substitution boxes. IEEE Access 9 , 93795-93802 (2021) sourceExperimental — accuracy not yet measured
The Chosen-Plaintext Attack section shows that one chosen image reveals the chaotic S-box, making the scheme studied vulnerable. The Brief Description of Understudy Scheme describes the S-box being generated before the input image is inserted, consistent with its independence from that image. The paper does not establish that this is the most substantial security threat to chaotic encryption algorithms generally; its analysis concerns Khan’s particular scheme. (LLM, conf=0.84)
- Not checked — no full text of the sourcecites [11] 11. Chen, J., Chen, L., Zhou, Y.: Cryptanalysis of a dnabased image encryption scheme. Information Sciences 520 , 130-141 (2020) source
- Disputedcites [28] 28. Ma, Y., Li, C., Ou, B.: Cryptanalysis of an image block encryption algorithm based on chaotic maps. Journal of Information Security and Applications 54 , 102566 (2020) sourceExperimental — accuracy not yet measured
Section 3.1 (page unavailable) says the pseudo-random sequence in the analyzed algorithm is closely related to the plain-image’s mean pixel value, contrary to the claimed nondependence. The paper does demonstrate a chosen-plaintext attack, but it does not identify nondependence as the most substantial threat to chaotic encryption algorithms. (LLM, conf=0.84)
Checked by a reasoning model — may be wrong.
plainstates a cause- 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.
- Partly supported
Some cited sources support this claim and some don’t — read each source’s verdict below.
In the paper
“The simultaneous permutation-diffusion approach presents no security risk to the cipher”
What the sources say
- Partly supportedcites [3] 3. Alanazi, A.S., Munir, N., Khan, M., Asif, M., Hussain, I.: Cryptanalysis of novel image encryption scheme based on multiple chaotic substitution boxes. IEEE Access 9 , 93795-93802 (2021) sourceExperimental — accuracy not yet measured
Section VI, “The Proposed Improvement” (page unavailable), proposes shuffling and bitwise addition to add diffusion. Section C, “Security Analysis” (page unavailable), calls the resulting cipher secure, but that cipher also uses substitution. The paper does not establish that a simultaneous permutation-diffusion approach alone presents no security risk. (LLM, conf=0.82)
- Not checked — no full text of the sourcecites [11] 11. Chen, J., Chen, L., Zhou, Y.: Cryptanalysis of a dnabased image encryption scheme. Information Sciences 520 , 130-141 (2020) source
- Disputedcites [28] 28. Ma, Y., Li, C., Ou, B.: Cryptanalysis of an image block encryption algorithm based on chaotic maps. Journal of Information Security and Applications 54 , 102566 (2020) sourceExperimental — accuracy not yet measured
The paper says the opposite about the cipher it analyzes. Section 4 (Conclusion; page unavailable) states that its equivalent secret key can be recovered with chosen plain-images and identifies security defects, rather than finding no security risk. (LLM, conf=0.87)
Checked by a reasoning model — may be wrong.
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.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Chaotic mathematical models have properties such as strong reactions to changes in initial conditions, randomlike behavior and ergodicity which are also desired for cryptography [5,7].”
What the sources say
- Partly supportedcites [5] 5. Alvarez, G., Li, S.: Some basic cryptographic requirements for chaos-based cryptosystems. Int J Bifurcat Chaos 16 (08), 2129-2151 (2006) sourceExperimental — accuracy not yet measured
Section 3.2 (pp. 5–6) says chaotic orbits diverge when parameters change slightly and that cryptographic keys should produce an avalanche effect. It discusses parameter changes rather than changes in initial conditions, and the passages found do not establish random-like behavior or ergodicity as desired cryptographic properties. (LLM, conf=0.84)
- Not checked — no full text of the sourcecites [7] 7. Bezerra, J.I.M., de Almeida Camargo, V.V., Molter, A.: A new efficient permutation-diffusion encryption algorithm based on a chaotic map. Chaos, Solitons & Fractals 151 , 111235 (2021) source
plainstates an association- 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.
- Partly supported
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
“43 times higher than the previously high for chaotic ciphers”
plainstates a cause- 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
“Throughput study shows that the cipher's performance improves considerably compared to other recently proposed parallel image encryption algorithms.”
boostedstates a cause- 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.
48 more claims
Create a free account to see all 94 claims and every source verdict.
- Probably not a substantial claim. 16
- It may state two separate claims as one. 29
- The quote only partly states this claim. 1
Citations
Cites
SOME BASIC CRYPTOGRAPHIC REQUIREMENTS FOR CHAOS-BASED CRYPTOSYSTEMS
ALVAREZ, G., & LI, S. (2006) · International Journal of Bifurcation and Chaos · doi:10.1142/s0218127406015970 · Cited by 2,119
Symmetric Ciphers Based on Two-Dimensional Chaotic Maps
Fridrich, J. (1998) · International Journal of Bifurcation and Chaos · doi:10.1142/s021812749800098x · Cited by 1,917
Rukhin, A., Sota, J., Nechvatal, J., Smid, M., Barker, E., Leigh, S., Levenson, M., Vangel, M., Banks, D., Heckert, A., et al. (2000) · doi:10.6028/nist.sp.800-22 · Cited by 1,867
Dang, S., Amin, O., Shihada, B., & Alouini, M.-S. (2020) · Nature Electronics · doi:10.1038/s41928-019-0355-6 · Cited by 1,790
Shafique, K., Khawaja, B. A., Sabir, F., Qazi, S., & Mustaqim, M. (2020) · IEEE Access · doi:10.1109/access.2020.2970118 · Cited by 1,352
Mathematics and Computers in Simulation
Cárdenas-Morales, D., Fraguela, A., & Garrancho, P. (2011) · Mathematics and Computers in Simulation · Cited by 621
IEEE Transactions on Parallel and Distributed Systems
(2023) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.71 · Cited by 583
A color image cryptosystem based on dynamic DNA encryption and chaos
Chai, X., Fu, X., Gan, Z., Lu, Y., & Chen, Y. (2019) · Signal Processing · doi:10.1016/j.sigpro.2018.09.029 · Cited by 573
A symmetric image encryption algorithm based on mixed linear–nonlinear coupled map lattice
Zhang, Y.-Q., & Wang, X.-Y. (2014) · Information Sciences · doi:10.1016/j.ins.2014.02.156 · Cited by 566
Journal of Parallel and Distributed Computing
Sdol, E. (2009) · Cited by 463
Metadata
- Authors
- Bezerra, J. I. M., Camargo, V. V. D. A., Soares, R. I., Molter, A., & Machado, G.
- Affiliations
- Universidade Federal de Pelotas
- Universidade Federal de Pelotas (BR)
- Venue
- Research Square
- Publisher
- Research Square Platform LLC
- Published
- 2024-04-08
- OpenAlex
- W4394580520
- Cited by
- 0
- References
- 52
- Type
- posted content
- Language
- en
- Open access
- green
- dx.doi.org
- Locations
- Research Square (acceptedVersion, cc-by)
- Funders
- Coordenação de Aperfeiçoamento de Pessoal de Nível Superior ((Code 001))
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Chaos-based Image/Signal Encryption
- Physical Sciences › Computer Science › Artificial Intelligence › Cryptographic Implementations and Security
- Physical Sciences › Computer Science › Artificial Intelligence › Computer Science and Engineering
- Keywords
- image encryption, chaotic maps, real-time encryption, encryption throughput, AES comparison, cryptanalysis attacks
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 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
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 novel single kernel parallel image encryption scheme based on a chaotic map. https://app.cochat.ai/papers/10.21203/rs.3.rs-4208203/v1
- The paper
- Bezerra, J. I. M., Camargo, V. V. D. A., Soares, R. I., Molter, A., & Machado, G. (2024). A novel single kernel parallel image encryption scheme based on a chaotic map. Research Square. https://doi.org/10.21203/rs.3.rs-4208203/v1
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.