QuanCrypt-FL: Enhancing Secure Federated Learning with Quantized Homomorphic Encryption and Pruning
QuanCrypt-FL leverages quantization, pruning, and homomorphic encryption to enable secure and efficient federated learning, mitigating inference attacks like gradient inversion while minimizing communication and computational overhead.
Privacy-Preserving Federated Learning with Differentially Private Hyperdimensional Computing (FedHDPrivacy)
FedHDPrivacy is a novel framework that enhances privacy in Federated Learning for IoT environments by combining Hyperdimensional Computing and Differential Privacy to protect sensitive data from model inversion and membership inference attacks while maintaining model accuracy.
FLiP: Using Dataset Distillation to Achieve Principle of Least Privilege in Federated Learning for Privacy Preservation
FLiP enhances privacy in Federated Learning by employing local-global dataset distillation, adhering to the Principle of Least Privilege, which minimizes shared information to only what's essential for model training, thereby mitigating privacy risks.
DPFedBank: A Federated Learning Framework for Financial Institutions Using Local Differential Privacy and Policy Pillars to Enhance Data Privacy
DPFedBank is a novel framework designed to enable financial institutions to collaboratively train machine learning models without sharing raw data, ensuring robust data privacy through Local Differential Privacy (LDP) and comprehensive policy enforcement.
FheFL: A Novel Federated Learning Algorithm for Privacy and Security Using Fully Homomorphic Encryption
FheFL is a new federated learning algorithm that uses fully homomorphic encryption (FHE) and a novel aggregation scheme based on users' non-poisoning rates to address both privacy and security concerns in federated learning environments.
Federated Learning with Reduced Information Leakage and Computational Cost
Upcycled-FL, a novel federated learning strategy that applies first-order approximation at every even round of model update, can significantly reduce information leakage and computational cost while maintaining model performance.
Immersion and Invariance-based Coding for Preserving Privacy in Federated Learning
A privacy-preserving federated learning framework is proposed that uses random coding and system immersion tools to protect the privacy of local and global models without compromising model performance or system efficiency.
Preserving Privacy in Federated Learning through Differential Privacy
Federated learning and differential privacy can be combined to enable large-scale machine learning over distributed datasets while providing rigorous privacy guarantees.
Federated Learning: Balancing Privacy and Accuracy
Collaborative federated learning protocols must balance privacy guarantees and model accuracy to be mutually beneficial for all participants.
Auditable Homomorphic-based Decentralized Collaborative AI with Attribute-based Differential Privacy
Proposing AerisAI for secure decentralized AI collaboration with differential privacy and homomorphic encryption.
© 2024 by Linnk AI