CoChat

Image Encryption Algorithm Combining Chaotic Image Encryption and Convolutional Neural Network

Open access
Feng, Luoyin, Du, Jize, Fu, Chong, Song, Wei · 2023 · Electronics

The DOI matches its Crossref record; 47 of the 47 references it cites were found in a registry or an index; 3 of the 9 sources its claims cite were checked for support.

Abstract

With the rapid development of information technology, the security of images has emerged as a significant area of research. This study presents an algorithm that integrates chaotic image encryption and a convolutional neural network (CNN) to enhance security and efficiency. The algorithm applies the properties of randomness and nonlinear mapping of chaotic sequences with the advanced feature extraction capabilities of a CNN model to achieve robust image encryption. First, we outline the fundamentals of chaotic image encryption and CNN. Chaotic image encryption employs chaotic sequence generation and nonlinear mapping to scramble pixel values for encryption purposes, while a CNN, as a deep-learning model with a local perceptual field and weight sharing, effectively extracts high-level image features. Subsequently, we provide a detailed description of the specific steps involved in combining chaotic image encryption and the CNN. These steps include chaotic sequence generation, pixel value mapping, feature extraction, and key management. The algorithm achieves high-strength encryption by performing dissimilarity operations between the chaotic sequence and image pixel values, as well as extracting high-level image features using the CNN. Finally, we conduct experimental evaluations of the algorithm and compare it with traditional chaotic image encryption methods. The experimental results demonstrate that the image encryption algorithm exhibits significant improvements in encrypti…

Overview

CoChat Summary

TL;DR

The paper proposes an image encryption algorithm that combines chaotic sequence generation and pixel scrambling with CNN-based feature extraction to improve security and efficiency. It reports higher PSNR/HU and faster encryption/decryption than traditional chaotic encryption, with comparisons to AES, DES, and RSA.

Key findings

  • In Table 1, the proposed Chaotic+CNN encryption achieved PSNR 41.78 dB, SSIM 0.95, and HU 0.92; traditional chaotic encryption had 35.21 dB, 0.92, and 0.78; AES had 41.52 dB, 0.96, and 0.88; DES had 38.90 dB, 0.94, and 0.82; RSA had 37.45 dB, 0.93, and 0.75. The paper states this is superior encryption quality/security, though the table shows AES had slightly higher SSIM (0.96 vs. 0.95).
  • Table 2 reports CNN+Chaotic Encryption as “Excellent” computational performance with “Fast” encryption and decryption speeds, versus traditional chaotic encryption as “High” computational performance with “Moderate” speeds.
  • Decrypted images were “basically identical” to originals, and encrypted images had more uniform histogram distributions, making statistical analysis harder.
  • In classification and hiding experiments, using chaotic-encrypted images as CNN inputs reportedly improved accuracy/robustness and allowed successful hiding/extraction of secret information; no numerical values are given.

Methods

  • Proposed design: chaotic sequence generation, pixel-value mapping/dissimilarity operations, CNN feature extraction, and key management; chaotic sequences can be CNN input, key generator, or fused with CNN feature maps.
  • Data: AI-TOD aerial image dataset for the encryption task; additional image sets for encryption/hiding; test samples included natural, facial, and digital images. AI-TOD was split into training/test; the hiding task was split into training/validation/test.
  • Evaluation: PSNR, SSIM, and HU; computational performance and encryption/decryption speed; comparisons with traditional chaotic encryption, AES, DES, RSA, and CNN+chaotic; hardware included an Intel Core i7 and NVIDIA GeForce RTX 3070.

Limitations

  • Stated: the authors call for further research/validation of robustness against attacks/interference, including statistical, differential, and brute-force attacks; key management/distribution; and efficiency/scalability for large-scale and real-time images.
  • Evident: many equations are missing/not decoded, and Table 1’s “Original Image” row is blank; Table 2 is ambiguously formatted. The paper also gives no sample sizes, CNN architecture/hyperparameters, or quantitative attack results, and its claim of higher SSIM than AES conflicts with Table 1 (AES 0.96 vs. proposed 0.95).

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

Integrity signals

Registry

Crossref · 10.3390/electronics12163455

Cites

47 of 47 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Verification

Claims the paper makes

0 Valid · 12 Not valid · 3 Not checked · 38 Own results and interpretations

12 more claims

Create a free account to see all 53 claims and every source verdict.

See all claims — free account
  • It may state two separate claims as one. 24
  • Borderline: one of the tests for a substantial claim is unclear. 1
  • Probably not a substantial claim. 18

Create a free account to see these claims.

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.

5 of 6 · the rest aren’t loaded

1 more finding

Create a free account to see every finding of this check.

See all findings — free account

Citations

Cites

Research works printed but not linked: 2

  1. Dichtl, M., and Golić, J.D. (2007). Cryptographic Hardware and Embedded Systems-CHES 2007, Proceedings of the 9th International Workshop, Vienna, Austria, 10–13 September 2007, Springer. Proceedings 9.
  2. Li, C., and Zhang, X. (2022). IoT and Big Data Technologies for Health Care, Springer.

Cited by

See all 58

Metadata

Authors
Feng, L., Du, J., Fu, C., & Song, W.
Affiliations
  • Northeastern University (CN)
  • University of Missouri (US)
Corresponding author
Feng, Luoyin
Venue
Electronics
Publisher
MDPI AG
Published
2023-08-15
Volume
12
Issue
16
Pages
3455
ISSN
2079-9292 (ISSN-L)
OpenAlex
W4385840071
Cited by
58
References
45
Citations by year
2026: 19 · 2025: 24 · 2024: 12 · 2023: 3
FWCI
5.27
Type
journal article
Language
en
Open access
Locations
Electronics (publishedVersion, cc-by)
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 › Computer Vision and Pattern Recognition › Advanced Steganography and Watermarking Techniques
Keywords
image encryption, chaotic image encryption, convolutional neural networks, chaotic sequence generation, pixel scrambling, image feature extraction, key management, encryption security, encryption speed

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

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.