Novel Privacy Preserving Non-Invasive Sensing-Based Diagnoses of Pneumonia Disease Leveraging Deep Network Model

Rehman, Mujeeb Ur; Shafique, Arslan; Khan, Kashif Hesham; Khalid, Sohail; Alotaibi, Abdullah Alhumaidi; Althobaiti, Turke; Ramzan, Naeem; Ahmad, Jawad; Shah, Syed Aziz; Abbasi, Qammer H.

doi:10.3390/s22020461

Cited by 14 publications

(5 citation statements)

References 76 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the last several decades, researchers have been exploring various methods to create S-boxes that are resilient against cryptographic attacks [77]. To evaluate the effectiveness of any new S-box design, it is important to compare its security features against existing S-boxes [35,47,[69][70][71][72]78,79].…”

Section: Comparison Analysis and Discussionmentioning

confidence: 99%

Chaos and Cellular Automata-Based Substitution Box and Its Application in Cryptography

et al. 2023

Self Cite

View full text Add to dashboard Cite

Substitution boxes are the key factor in symmetric-key cryptosystems that determines their ability to resist various cryptanalytic attacks. Creating strong substitution boxes that have multiple strong cryptographic properties at the same time is a challenging task for cryptographers. A significant amount of research has been conducted on S-boxes in the past few decades, but the resulting S-boxes have been found to be vulnerable to various cyberattacks. This paper proposes a new method for creating robust S-boxes that exhibit superior performance and possess high scores in multiple cryptographic properties. The hybrid S-box method presented in this paper is based on Chua’s circuit chaotic map, two-dimensional cellular automata, and an algebraic permutation group structure. The proposed 16×16 S-box has an excellent performance in terms of security parameters, including a minimum nonlinearity of 102, the absence of fixed points, the satisfaction of bit independence and strict avalanche criteria, a low differential uniformity of 5, a low linear approximation probability of 0.0603, and an auto-correlation function of 28. The analysis of the performance comparison indicates that the proposed S-box outperforms other state-of-the-art S-box techniques in several aspects. It possesses better attributes, such as a higher degree of inherent security and resilience, which make it more secure and less vulnerable to potential attacks.

show abstract

Section: Comparison Analysis and Discussionmentioning

confidence: 99%

Chaos and Cellular Automata-Based Substitution Box and Its Application in Cryptography

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…The author of this study describes non-invasive sensing-based diagnostics of pneumonia disease that maintain security while utilizing a deep learning model to make the procedure non-invasive [45]. The proposed approach is split into two parts.…”

Section: Pneumothorax Detection Privacymentioning

confidence: 99%

Chest Radiographs Based Pneumothorax Detection Using Federated Learning

Almadhor¹,

Khan²,

Wechtaisong³

et al. 2023

Computer Systems Science and Engineering

View full text Add to dashboard Cite

Pneumothorax is a thoracic condition that occurs when a person's lungs collapse, causing air to enter the pleural cavity, the area close to the lungs and chest wall. The most persistent disease, as well as one that necessitates particular patient care and the privacy of their health records. The radiologists find it challenging to diagnose pneumothorax due to the variations in images. Deep learning-based techniques are commonly employed to solve image categorization and segmentation problems. However, it is challenging to employ it in the medical field due to privacy issues and a lack of data. To address this issue, a federated learning framework based on an Xception neural network model is proposed in this research. The pneumothorax medical image dataset is obtained from the Kaggle repository. Data preprocessing is performed on the used dataset to convert unstructured data into structured information to improve the model's performance. Min-max normalization technique is used to normalize the data, and the features are extracted from chest Xray images. Then dataset converts into two windows to make two clients for local model training. Xception neural network model is trained on the dataset individually and aggregates model updates from two clients on the server side. To decrease the over-fitting effect, every client analyses the results three times. Client 1 performed better in round 2 with a 79.0% accuracy, and client 2 performed better in round 2 with a 77.0% accuracy. The experimental result shows the effectiveness of the federated learning-based technique on a deep neural network, reaching a 79.28% accuracy while also providing privacy to the patient's data.

show abstract

“…In the last several decades, researchers have explored various methods to create Sboxes resilient against cryptographic attacks [39]. A comparison of our proposed S-boxes with existing ones is made in Table 10 to evaluate not only its effectiveness but also its security features.…”

Section: Comparative Analysis Of the Proposed Algorithmmentioning

confidence: 99%

Chaos Meets Cryptography: Developing an S-Box Design with the Rössler Attractor

Corona-Bermúdez,

Chimal-Eguía,

Corona-Bermúdez

et al. 2023

Mathematics

View full text Add to dashboard Cite

The volume of data transmitted over networks has significantly increased in recent years. For that reason, safeguarding the privacy, authenticity, and confidentiality of specific data is imperative, necessitating a type of encryption; symmetric encryption, known for its computational efficiency, is ideal for securing extensive datasets. A principal component within symmetric key algorithms is the substitution box (S-box), which creates confusion between plaintext and ciphertext, enhancing the security of the process. This paper proposes a fashion method to create chaotic S-boxes using the Rössler attractor as a chaotic process and the Rijndael S-box as a permutation box. The proposed S-boxes are evaluated with bijectivity, non-linearity (NL), strict avalanche criterion (SAC), bit independence criterion (BIC), linear approximation probability (LAP), and differential uniformity (DU). The analyses show that the proposed method helps generate a high-resistance S-box to well-known attacks and high efficiency, executing in short computational time.

show abstract

Novel Privacy Preserving Non-Invasive Sensing-Based Diagnoses of Pneumonia Disease Leveraging Deep Network Model

Cited by 14 publications

References 76 publications

Chaos and Cellular Automata-Based Substitution Box and Its Application in Cryptography

Chaos and Cellular Automata-Based Substitution Box and Its Application in Cryptography

Chest Radiographs Based Pneumothorax Detection Using Federated Learning

Chaos Meets Cryptography: Developing an S-Box Design with the Rössler Attractor

Contact Info

Product

Resources

About