Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

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 access
Bezerra, Joao Inacio Moreira, Camargo, Vinícius Valduga de Almeida, Soares, Rafael Iankowski, Molter, Alexandre, Machado, Gustavo · 2024 · Research Square

Abstract

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

Crossref · 10.21203/rs.3.rs-4208203/v1

Cites

53 of 53 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Verification

Claims the paper makes

4 Valid · 4 Not valid · 40 Not checked · 46 Own results and interpretations

48 more claims

Create a free account to see all 94 claims and every source verdict.

See all claims — free account
  • Probably not a substantial claim. 16
  • It may state two separate claims as one. 29
  • The quote only partly states this claim. 1

Create a free account to see these claims.

Citations

Cites

Show all 52 references

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
Published
2024-04-08
OpenAlex
W4394580520
Cited by
0
References
52
Type
posted content
Language
en
Open access
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.