相关论文: Training on Fake Labels: Mitigating Label Leakage …

In distributed learning settings, models are iteratively updated with shared gradients computed from potentially sensitive user data. While previous work has studied various privacy risks of sharing gradients, our paper aims to provide a…

Split learning (SL) has been proposed to train deep learning models in a decentralized manner. For decentralized healthcare applications with vertical data partitioning, SL can be beneficial as it allows institutes with complementary…

In the era of a data-driven society with the ubiquity of Internet of Things (IoT) devices storing large amounts of data localized at different places, distributed learning has gained a lot of traction, however, assuming independent and…

Noisy labels are an unavoidable consequence of labeling processes and detecting them is an important step towards preventing performance degradations in Convolutional Neural Networks. Discarding noisy labels avoids a harmful memorization,…

Federated Learning (FL) allows for the training of Machine Learning models in a collaborative manner without the need to share sensitive data. However, it remains vulnerable to Gradient Leakage Attacks (GLAs), which can reveal private…

Transfer learning (TL) has been demonstrated to improve DNN model performance when faced with a scarcity of training samples. However, the suitability of TL as a solution to reduce vulnerability of overfitted DNNs to privacy attacks is…

Collaborative learning (CL) is a distributed learning framework that aims to protect user privacy by allowing users to jointly train a model by sharing their gradient updates only. However, gradient inversion attacks (GIAs), which recover…

Differential privacy (DP) techniques can be applied to the federated learning model to protect data privacy against inference attacks to communication among the learning agents. The DP techniques, however, hinder achieving a greater…

With the vigorous development of artificial intelligence technology, various engineering technology applications have been implemented one after another. The gradient descent method plays an important role in solving various optimization…

Personalized Large Language Models (LLMs) have become increasingly prevalent, showcasing the impressive capabilities of models like GPT-4. This trend has also catalyzed extensive research on deploying LLMs on mobile devices. Feasible…

Federated learning (FL) allows the collaborative training of AI models without needing to share raw data. This capability makes it especially interesting for healthcare applications where patient and data privacy is of utmost concern.…

Federated Learning (FL) enables collaborative model building among a large number of participants without the need for explicit data sharing. But this approach shows vulnerabilities when privacy inference attacks are applied to it. In…

Federated Learning (FL) enables collaborative training of models across distributed clients without sharing local data, addressing privacy concerns in decentralized systems. However, the gradient-sharing process exposes private data to…

We propose a novel end-to-end privacy-preserving framework, instantiated by three efficient protocols for different deployment scenarios, covering both input and output privacy, for the vertically split scenario in federated learning (FL),…

Everyday, large amounts of sensitive data is distributed across mobile phones, wearable devices, and other sensors. Traditionally, these enormous datasets have been processed on a single system, with complex models being trained to make…

Federated Learning (FL) enables collaborative model training across distributed clients without sharing raw data, making it a promising approach for privacy-preserving machine learning in domains like Connected and Autonomous Vehicles…

Federated Learning (FL) enables collaborative model training while preserving data privacy by keeping raw data locally stored on client devices, preventing access from other clients or the central server. However, recent studies reveal that…

Vertical Federated Learning (VFL) is widely utilized in real-world applications to enable collaborative learning while protecting data privacy and safety. However, previous works show that parties without labels (passive parties) in VFL can…

Federated Learning allows collaborative training without data sharing in settings where participants do not trust the central server and one another. Privacy can be further improved by ensuring that communication between the participants…

This article presents DDP-SA, a scalable privacy-preserving federated learning framework that jointly leverages client-side local differential privacy (LDP) and full-threshold additive secret sharing (ASS) for secure aggregation. Unlike…