33 citations · 46 across the 13 of their papers we have counts for
13 papers
FourierCompress: Layer-Aware Spectral Activation Compression for Efficient and Accurate Collaborative LLM Inference
Jian Ma, Xinchen Lyu, Jun Jiang +4
Collaborative large language model (LLM) inference enables real-time, privacy-preserving AI services on resource-constrained edge devices by partitioning computational workloads be…
Agile Orchestration at Will: An Entire Smart Service-Based Security Architecture Towards 6G
Zhuoran Duan, Guoshun Nan, Rushan Li +8
The upcoming 6G will fundamentally reshape mobile networks beyond communications, unlocking a multitude of applications that were once considered unimaginable. Meanwhile, security…
Convergence-Privacy-Fairness Trade-Off in Personalized Federated Learning
Xiyu Zhao, Qimei Cui, Weicai Li +5
Personalized federated learning (PFL), e.g., the renowned Ditto, strikes a balance between personalization and generalization by conducting federated learning (FL) to guide persona…
A Novel Indicator for Quantifying and Minimizing Information Utility Loss of Robot Teams
Xiyu Zhao, Qimei Cui, Wei Ni +5
The timely exchange of information among robots within a team is vital, but it can be constrained by limited wireless capacity. The inability to deliver information promptly can re…
Enhancing Convergence, Privacy and Fairness for Wireless Personalized Federated Learning: Quantization-Assisted Min-Max Fair Scheduling
Xiyu Zhao, Qimei Cui, Ziqiang Du +6
Personalized federated learning (PFL) offers a solution to balancing personalization and generalization by conducting federated learning (FL) to guide personalized learning (PL). L…
Two Is Better Than One: Rotations Scale LoRAs
Hongcan Guo, Guoshun Nan, Yuan Yang +9
Scaling Low-Rank Adaptation (LoRA)-based Mixture-of-Experts (MoE) facilitates large language models (LLMs) to efficiently adapt to diverse tasks. However, traditional gating mechan…
An LLM-based Self-Evolving Security Framework for 6G Space-Air-Ground Integrated Networks
Qi Qin, Xinye Cao, Guoshun Nan +8
Recently emerged 6G space-air-ground integrated networks (SAGINs), which integrate satellites, aerial networks, and terrestrial communications, offer ubiquitous coverage for variou…
Generative AI for Physical-Layer Authentication
Rui Meng, Xiqi Cheng, Song Gao +6
Recently, Artificial Intelligence (AI)-driven Physical-Layer Authentication (PLA), which focuses on achieving endogenous security and intelligent identity authentication, has attra…
SplitFrozen: Split Learning with Device-side Model Frozen for Fine-Tuning LLM on Heterogeneous Resource-Constrained Devices
Jian Ma, Xinchen Lyu, Jun Jiang +3
Fine-tuning large language models (LLMs) on private, on-device data can empower tailored personalized AI agents. However, fine-tuning LLMs on resource-constrained edge devices face…
Channel Estimation, Interpolation and Extrapolation in Doubly-dispersive Channels
Zijun Gong, Fan Jiang, Yuhui Song +2
The OTFS (Orthogonal Time Frequency Space) is widely acknowledged for its ability to combat Doppler spread in time-varying channels. In this paper, another advantage of OTFS over O…
MALSIGHT: Exploring Malicious Source Code and Benign Pseudocode for Iterative Binary Malware Summarization
Haolang Lu, Hongrui Peng, Guoshun Nan +6
Binary malware summarization aims to automatically generate human-readable descriptions of malware behaviors from executable files, facilitating tasks like malware cracking and det…
Semantic Entropy Can Simultaneously Benefit Transmission Efficiency and Channel Security of Wireless Semantic Communications
Yankai Rong, Guoshun Nan, Minwei Zhang +9
Recently proliferated deep learning-based semantic communications (DLSC) focus on how transmitted symbols efficiently convey a desired meaning to the destination. However, the sens…
Similarity-based Label Inference Attack against Training and Inference of Split Learning
Junlin Liu, Xinchen Lyu, Qimei Cui +1
Split learning is a promising paradigm for privacy-preserving distributed learning. The learning model can be cut into multiple portions to be collaboratively trained at the partic…