Tootfinder

Ukraine covers Europe: the West loses the initiative while the Russian Federation arms itself: https://benborges.xyz/2025/07/06/ukraine-covers-europe-the-west.html

FedQuad: Federated Stochastic Quadruplet Learning to Mitigate Data Heterogeneity
Ozgu Goksu, Nicolas Pugeault
https://arxiv.org/abs/2509.04107 https://arxi…

FedQuad: Federated Stochastic Quadruplet Learning to Mitigate Data Heterogeneity
Federated Learning (FL) provides decentralised model training, which effectively tackles problems such as distributed data and privacy preservation. However, the generalisation of global models frequently faces challenges from data heterogeneity among clients. This challenge becomes even more pronounced when datasets are limited in size and class imbalance. To address data heterogeneity, we propose a novel method, \textit{FedQuad}, that explicitly optimises smaller intra-class variance and larg…

FedPromo: Federated Lightweight Proxy Models at the Edge Bring New Domains to Foundation Models
Matteo Caligiuri, Francesco Barbato, Donald Shenaj, Umberto Michieli, Pietro Zanuttigh
https://arxiv.org/abs/2508.03356

FedPromo: Federated Lightweight Proxy Models at the Edge Bring New Domains to Foundation Models
Federated Learning (FL) is an established paradigm for training deep learning models on decentralized data. However, as the size of the models grows, conventional FL approaches often require significant computational resources on client devices, which may not be feasible. We introduce FedPromo, a novel framework that enables efficient adaptation of large-scale foundation models stored on a central server to new domains encountered only by remote clients. Instead of directly training the large m…

Coward: Toward Practical Proactive Federated Backdoor Defense via Collision-based Watermark
Wenjie Li, Siying Gu, Yiming Li, Kangjie Chen, Zhili Chen, Tianwei Zhang, Shu-Tao Xia, Dacheng Tao
https://arxiv.org/abs/2508.02115

Coward: Toward Practical Proactive Federated Backdoor Defense via Collision-based Watermark
Backdoor detection is currently the mainstream defense against backdoor attacks in federated learning (FL), where malicious clients upload poisoned updates that compromise the global model and undermine the reliability of FL deployments. Existing backdoor detection techniques fall into two categories, including passive and proactive ones, depending on whether the server proactively modifies the global model. However, both have inherent limitations in practice: passive defenses are vulnerable to…

"On June 25th, 1999, Brian Foote published a seminal article that became, for a short while, one of the most commented pages of the early Internet, at least by struggling software developers and prospective architects. Such was the impact that it “was twice featured in Slashdot” (kids: that is the 1999 equivalent of “this article hit the homepage of Hacker News”). After almost 25 years since that publication, one question lingers: when are we going to accept defeat?"

FedAPTA: Federated Multi-task Learning in Computing Power Networks with Adaptive Layer-wise Pruning and Task-aware Aggregation
Yachao Yuan, Zhen Yu, Jin Wang, Zhipeng Cheng, Jianhua Hu
https://arxiv.org/abs/2508.02230

FedAPTA: Federated Multi-task Learning in Computing Power Networks with Adaptive Layer-wise Pruning and Task-aware Aggregation
Federated Learning (FL) has shown considerable promise in Computing Power Networks (CPNs) for privacy protection, efficient data utilization, and dynamic collaboration. Although it offers practical benefits, applying FL in CPNs continues to encounter a major obstacle, i.e., multi-task deployment. However, existing work mainly focuses on mitigating FL's computation and communication overhead of a single task while overlooking the computing resource wastage issue of heterogeneous devices across m…

Feature Reconstruction Aided Federated Learning for Image Semantic Communication
Yoon Huh, Bumjun Kim, Wan Choi
https://arxiv.org/abs/2508.02048 https://ar…

Feature Reconstruction Aided Federated Learning for Image Semantic Communication
Research in semantic communication has garnered considerable attention, particularly in the area of image transmission, where joint source-channel coding (JSCC)-based neural network (NN) modules are frequently employed. However, these systems often experience performance degradation over time due to an outdated knowledge base, highlighting the need for periodic updates. To address this challenge in the context of training JSCC modules for image transmission, we propose a federated learning (FL)…

It is difficult to imagine the devastation of a nuclear war.
Our team at the Federation of American Scientists asked Sébastien Philippe, a research scholar with Princeton University’s Program on Science and Global Security,
who models the effects of nuclear weapons and the consequences of nuclear war,
to help us visualize what an attack on Washington could look like

This is how a nuclear attack on the U.S. might unfold
A scenario of America’s response to an incoming nuclear attack.

Warming Up for Zeroth-Order Federated Pre-Training with Low Resource Clients
Gwen Legate, Irina Rish, Eugene Belilovsky
https://arxiv.org/abs/2509.03503 https://

Warming Up for Zeroth-Order Federated Pre-Training with Low Resource Clients
Federated learning enables collaborative model training across numerous edge devices without requiring participants to share data; however, memory and communication constraints on these edge devices may preclude their participation in training. We consider a setting in which a subset of edge devices are below a critical memory or communication threshold required to conduct model updates. Under typical federated optimization algorithms, these devices are excluded from training which renders thei…

FedGuard: A Diverse-Byzantine-Robust Mechanism for Federated Learning with Major Malicious Clients
Haocheng Jiang, Hua Shen, Jixin Zhang, Willy Susilo, Mingwu Zhang
https://arxiv.org/abs/2508.00636

FedGuard: A Diverse-Byzantine-Robust Mechanism for Federated Learning with Major Malicious Clients
Federated learning is a distributed training framework vulnerable to Byzantine attacks, particularly when over 50% of clients are malicious or when datasets are highly non-independent and identically distributed (non-IID). Additionally, most existing defense mechanisms are designed for specific attack types (e.g., gradient similarity-based schemes can only defend against outlier model poisoning), limiting their effectiveness. In response, we propose FedGuard, a novel federated learning mechanis…