Homomorphic Encryption-Based Federated Privacy Preservation for Deep Active Learning

Kurniawan, Hendra; Mambo, Masahiro

doi:10.3390/e24111545

Cited by 10 publications

(6 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…, n Therefore, DeepAL generates another label training set S N . The entropy of class prediction information is chosen using Equation (1) as described in Algorithm 1 [53,56,57]. Step 2: Use entropy analysis to select the unlabeled samples with the greatest degree of uncertainty S i where it has the class prediction information with the highest entropy by using the following equation:…”

Section: Deep Active Learningmentioning

confidence: 99%

“…A blockchain-federated learning architecture is proposed for complete decentralization and enhanced security. Furthermore, decentralization increases the model's accuracy and makes it poisoning-proof [56]. Although FL provides privacy-preserving training with distributed data, adversaries can still reveal sensitive information by sharing weights.…”

Section: Homomorphic Encryption (He)mentioning

confidence: 99%

See 1 more Smart Citation

Smart Flood Detection with AI and Blockchain Integration in Saudi Arabia Using Drones

Alsumayt

El-Haggar

Amouri

et al. 2023

Sensors

View full text Add to dashboard Cite

Global warming and climate change are responsible for many disasters. Floods pose a serious risk and require immediate management and strategies for optimal response times. Technology can respond in place of humans in emergencies by providing information. As one of these emerging artificial intelligence (AI) technologies, drones are controlled in their amended systems by unmanned aerial vehicles (UAVs). In this study, we propose a secure method of flood detection in Saudi Arabia using a Flood Detection Secure System (FDSS) based on deep active learning (DeepAL) based classification model in federated learning to minimize communication costs and maximize global learning accuracy. We use blockchain-based federated learning and partially homomorphic encryption (PHE) for privacy protection and stochastic gradient descent (SGD) to share optimal solutions. InterPlanetary File System (IPFS) addresses issues with limited block storage and issues posed by high gradients of information transmitted in blockchains. In addition to enhancing security, FDSS can prevent malicious users from compromising or altering data. Utilizing images and IoT data, FDSS can train local models that detect and monitor floods. A homomorphic encryption technique is used to encrypt each locally trained model and gradient to achieve ciphertext-level model aggregation and model filtering, which ensures that the local models can be verified while maintaining privacy. The proposed FDSS enabled us to estimate the flooded areas and track the rapid changes in dam water levels to gauge the flood threat. The proposed methodology is straightforward, easily adaptable, and offers recommendations for Saudi Arabian decision-makers and local administrators to address the growing danger of flooding. This study concludes with a discussion of the proposed method and its challenges in managing floods in remote regions using artificial intelligence and blockchain technology.

show abstract

Section: Deep Active Learningmentioning

confidence: 99%

Section: Homomorphic Encryption (He)mentioning

confidence: 99%

Smart Flood Detection with AI and Blockchain Integration in Saudi Arabia Using Drones

Alsumayt

El-Haggar

Amouri

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…In [18], authors worked on homomorphic encryption-based federated learning techniques for maximizing machine learning performance. They proposed a privacy-preserving technique for active learning.…”

Section: Related Workmentioning

confidence: 99%

Secret learning for lung cancer diagnosis—a study with homomorphic encryption, texture analysis and deep learning

Adhikary,

Dutta,

Dwivedi

2023

Biomed. Phys. Eng. Express

View full text Add to dashboard Cite

Advanced lung cancer diagnoses from radiographic images include automated detection of lung cancer from CT-Scan images of the lungs. Deep learning is a popular method for decision making which can be used to classify cancerous and non-cancerous lungs from CT-Scan images. There are many experiments which show the uses of deep learning for performing such classifications but very few of them have preserved the privacy of users. Among existing methods, federated learning limits data sharing to a central server and differential privacy although increases anonymity the original data is still shared. Homomorphic encryption can resolve the limitations of both of these. Homomorphic encryption is a cryptographic technique that allows computations to be performed on encrypted data. In our experiment, we have proposed a series of textural information extraction with the implementation of homomorphic encryption of the CT-Scan images of normal, adenocarcinoma, large cell carcinoma and squamous cell carcinoma. We have further processed the encrypted data to make it classifiable and later we have classified it with deep learning. The results from the experiments have obtained a classification accuracy of 0.9347.

show abstract

“…The algorithm finds applications in various settings, including enterprise, IoT-enabled healthcare systems, and deep active learning (Kurniawan & Mambo, 2022;Song, 2022;Sattar & Gaata, 2017). Additionally, it can train machine learning models to extract knowledge from training data that cannot be directly accessed (Baracaldo & Shaul, 2023).…”

Section: Applicationsmentioning

confidence: 99%

“…Rahulamathavan (2023), This paper proposes a novel federated learning algorithm based on fully homomorphic encryption that can protect against Byzantine attacks. Kurniawan & Mambo (2022), This article discusses how federated learning can be combined with homomorphic encryption to preserve privacy while training machine learning models. , This paper proposes a homomorphic encryption-based federated learning scheme to preserve privacy in active learning scenarios.…”

Section: Introductionmentioning

confidence: 99%

Secure Federated Learning with a Homomorphic Encryption Model

Hussien,

Salman

et al. 2023

IJPASR

View full text Add to dashboard Cite

Federated learning (FL) offers collaborative machine learning across decentralized devices while safeguarding data privacy. However, data security and privacy remain key concerns. This paper introduces "Secure Federated Learning with a Homomorphic Encryption Model," addressing these challenges by integrating homomorphic encryption into FL. The model starts by initializing a global machine learning model and generating a homomorphic encryption key pair, with the public key shared among FL participants. Using this public key, participants then collect, preprocess, and encrypt their local data. During FL Training Rounds, participants decrypt the global model, compute local updates on encrypted data, encrypt these updates, and securely send them to the aggregator. The aggregator homomorphic ally combines updates without revealing participant data, forwarding the encrypted aggregated update to the global model owner. The Global Model Update ensures the owner decrypts the aggregated update using the private key, updates the global model, encrypts it with the public key, and shares the encrypted global model with FL participants. With optional model evaluation, training can iterate for several rounds or until convergence. This model offers a robust solution to Florida data privacy and security issues, with versatile applications across domains. This paper presents core model components, advantages, and potential domain-specific implementations while making significant strides in addressing FL's data privacy concerns.

show abstract

Homomorphic Encryption-Based Federated Privacy Preservation for Deep Active Learning

Cited by 10 publications

References 21 publications

Smart Flood Detection with AI and Blockchain Integration in Saudi Arabia Using Drones

Smart Flood Detection with AI and Blockchain Integration in Saudi Arabia Using Drones

Secret learning for lung cancer diagnosis—a study with homomorphic encryption, texture analysis and deep learning

Secure Federated Learning with a Homomorphic Encryption Model

Contact Info

Product

Resources

About