Tootfinder

This https://arxiv.org/abs/2212.01976 has been replaced.
link: https://scholar.google.com/scholar?q=a

FedCC: Robust Federated Learning against Model Poisoning Attacks
Federated Learning, designed to address privacy concerns in learning models, introduces a new distributed paradigm that safeguards data privacy but differentiates the attack surface due to the server's inaccessibility to local datasets and the change in protection objective--parameters' integrity. Existing approaches, including robust aggregation algorithms, fail to effectively filter out malicious clients, especially those with non-Independently and Identically Distributed data. Furthermore, t…

Gefragt wird beim #4CultureCommunityPlenary, wie man Metadaten eines Projektes in den Culture Knowledge Graph integrieren kann.
➡️ Hierzu gibt es die CGIF Specification: https://nfdi4culture.de/go/E3712

This https://arxiv.org/abs/2404.10635 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDC_…

Compressed Federated Reinforcement Learning with a Generative Model
Reinforcement learning has recently gained unprecedented popularity, yet it still grapples with sample inefficiency. Addressing this challenge, federated reinforcement learning (FedRL) has emerged, wherein agents collaboratively learn a single policy by aggregating local estimations. However, this aggregation step incurs significant communication costs. In this paper, we propose CompFedRL, a communication-efficient FedRL approach incorporating both \textit{periodic aggregation} and (direct/erro…

This https://arxiv.org/abs/2405.13766 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

The Power of Extrapolation in Federated Learning
We propose and study several server-extrapolation strategies for enhancing the theoretical and empirical convergence properties of the popular federated learning optimizer FedProx [Li et al., 2020]. While it has long been known that some form of extrapolation can help in the practice of FL, only a handful of works provide any theoretical guarantees. The phenomenon seems elusive, and our current theoretical understanding remains severely incomplete. In our work, we focus on smooth convex or stro…

This https://arxiv.org/abs/2212.01976 has been replaced.
link: https://scholar.google.com/scholar?q=a

FedCC: Robust Federated Learning against Model Poisoning Attacks
Federated Learning, designed to address privacy concerns in learning models, introduces a new distributed paradigm that safeguards data privacy but differentiates the attack surface due to the server's inaccessibility to local datasets and the change in protection objective--parameters' integrity. Existing approaches, including robust aggregation algorithms, fail to effectively filter out malicious clients, especially those with non-Independently and Identically Distributed data. Furthermore, t…

This https://arxiv.org/abs/2404.15611 has been replaced.
link: https://scholar.google.com/scholar?q=a

Model Poisoning Attacks to Federated Learning via Multi-Round Consistency
Model poisoning attacks are critical security threats to Federated Learning (FL). Existing model poisoning attacks suffer from two key limitations: 1) they achieve suboptimal effectiveness when defenses are deployed, and/or 2) they require knowledge of the model updates or local training data on genuine clients. In this work, we make a key observation that their suboptimal effectiveness arises from only leveraging model-update consistency among malicious clients within individual training round…

This https://arxiv.org/abs/2404.15611 has been replaced.
link: https://scholar.google.com/scholar?q=a

Model Poisoning Attacks to Federated Learning via Multi-Round Consistency
Model poisoning attacks are critical security threats to Federated Learning (FL). Existing model poisoning attacks suffer from two key limitations: 1) they achieve suboptimal effectiveness when defenses are deployed, and/or 2) they require knowledge of the model updates or local training data on genuine clients. In this work, we make a key observation that their suboptimal effectiveness arises from only leveraging model-update consistency among malicious clients within individual training round…

This https://arxiv.org/abs/2405.20975 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

ACE: A Model Poisoning Attack on Contribution Evaluation Methods in Federated Learning
In Federated Learning (FL), a set of clients collaboratively train a machine learning model (called global model) without sharing their local training data. The local training data of clients is typically non-i.i.d. and heterogeneous, resulting in varying contributions from individual clients to the final performance of the global model. In response, many contribution evaluation methods were proposed, where the server could evaluate the contribution made by each client and incentivize the high-…

From The Real News
@…
The prison system isn't 'broken'—it's designed to traumatize Black people en masse https://

The prison system isn’t ‘broken’—it’s designed to traumatize Black people en masse
Traumatologist Dr. Da'Mond Holt discusses the ways mass incarceration inflicts deliberate trauma as strategy to oppress working class people of color.

Privacy-preserving Quantification of Non-IID Degree in Federated Learning
Yuping Yan, Yizhi Wang, Yingchao Yu, Yaochu Jin
https://arxiv.org/abs/2406.09682 …

Privacy-preserving Quantification of Non-IID Degree in Federated Learning
Federated learning (FL) offers a privacy-preserving approach to machine learning for multiple collaborators without sharing raw data. However, the existence of non-independent and non-identically distributed (non-IID) datasets across different clients presents a significant challenge to FL, leading to a sharp drop in accuracy, reduced efficiency, and hindered implementation. To address the non-IID problem, various methods have been proposed, including clustering and personalized FL frameworks. …