42 citations · 43 across the 9 of their papers we have counts for
11 papers
Byzantine-Resilient Federated Large Language Model via Hypergraph Message Passing
Kai Li, Hanlin Cai, Zihao Liu +5
Federated Large Language Models (FedLLMs) are promising to deliver privacy-preserving, collaborative intelligence. The decentralized training process is vulnerable to Byzantine att…
FedLNS: Leverage LayerNorm Signature Modeling to Mitigate Adversarial Manipulation in Federated LLMs
Kai Li, Jong-Ik Park, Carlee Joe-Wong +2
Federated training enables language models to learn from distributed private text, but the server cannot directly verify the local supervision or optimization process that produces…
Sharing is Caring: Analysis of Hybrid Network Sharing Strategies for Energy Efficient Multi-Operator Cellular Systems
Laura Finarelli, Maoquan Ni, Michela Meo +2
This paper introduces a novel analytical framework for evaluating energy-efficient, QoS-aware network-sharing strategies in cellular networks. Leveraging stochastic geometry, our f…
Assessing the Benefits of Ground Vehicles as Moving Urban Base Stations
Laura Finarelli, Falko Dressler, Marco Ajmone Marsan +1
In the evolution towards 6G user-centric networking, the moving network (MN) paradigm can play an important role. In a MN, some small cell base stations (BS) are installed on top o…
Zero-Trust Foundation Models: A New Paradigm for Secure and Collaborative Artificial Intelligence for Internet of Things
Kai Li, Conggai Li, Xin Yuan +8
This paper focuses on Zero-Trust Foundation Models (ZTFMs), a novel paradigm that embeds zero-trust security principles into the lifecycle of foundation models (FMs) for Internet o…
Undermining Federated Learning Accuracy in EdgeIoT via Variational Graph Auto-Encoders
Kai Li, Shuyan Hu, Bochun Wu +3
EdgeIoT represents an approach that brings together mobile edge computing with Internet of Things (IoT) devices, allowing for data processing close to the data source. Sending sour…
Towards Resilient Federated Learning in CyberEdge Networks: Recent Advances and Future Trends
Kai Li, Zhengyang Zhang, Azadeh Pourkabirian +3
In this survey, we investigate the most recent techniques of resilient federated learning (ResFL) in CyberEdge networks, focusing on joint training with agglomerative deduction and…
Personalized and Context-aware Route Planning for Edge-assisted Vehicles
Dinesh Cyril Selvaraj, Falko Dressler, Carla Fabiana Chiasserini
Conventional route planning services typically offer the same routes to all drivers, focusing primarily on a few standardized factors such as travel distance or time, overlooking i…
Mobile Networks on the Move: Optimizing Moving Base Stations Dynamics in Urban Scenarios
Laura Finarelli, Falko Dressler, Marco Marsan Ajmone +1
Base station densification is one of the key approaches for delivering high capacity in radio access networks. However, current static deployments are often impractical and financi…
Leverage Variational Graph Representation For Model Poisoning on Federated Learning
Kai Li, Xin Yuan, Jingjing Zheng +3
This paper puts forth a new training data-untethered model poisoning (MP) attack on federated learning (FL). The new MP attack extends an adversarial variational graph autoencoder…
V-Edge: Virtual Edge Computing as an Enabler for Novel Microservices and Cooperative Computing
Falko Dressler, Carla Fabiana Chiasserini, Frank H. P. Fitzek +8
As we move from 5G to 6G, edge computing is one of the concepts that needs revisiting. Its core idea is still intriguing: instead of sending all data and tasks from an end user's d…