activity
20222024
most citedPersonal LLM Agents: Insights and Survey about the Capability, Efficiency and Security

31 citations · 57 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CR2024

A First Look At Efficient And Secure On-Device LLM Inference Against KV Leakage

Huan Yang, Deyu Zhang, Yudong Zhao +2

Running LLMs on end devices has garnered significant attention recently due to their advantages in privacy preservation. With the advent of lightweight LLM models and specially des…

cs.OS20245 cited

LLM as a System Service on Mobile Devices

Wangsong Yin, Mengwei Xu, Yuanchun Li +1

Being more powerful and intrusive into user-device interactions, LLMs are eager for on-device execution to better preserve user privacy. In this work, we propose a new paradigm of…

cs.HC202431 cited

Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security

Yuanchun Li, Hao Wen, Weijun Wang +22

Since the advent of personal computing devices, intelligent personal assistants (IPAs) have been one of the key technologies that researchers and engineers have focused on, aiming…

cs.LG202311 cited

PatchBackdoor: Backdoor Attack against Deep Neural Networks without Model Modification

Yizhen Yuan, Rui Kong, Shenghao Xie +2

Backdoor attack is a major threat to deep learning systems in safety-critical scenarios, which aims to trigger misbehavior of neural network models under attacker-controlled condit…

cs.LG20232 cited

AdaptiveNet: Post-deployment Neural Architecture Adaptation for Diverse Edge Environments

Hao Wen, Yuanchun Li, Zunshuai Zhang +5

Deep learning models are increasingly deployed to edge devices for real-time applications. To ensure stable service quality across diverse edge environments, it is highly desirable…

cs.LG20228 cited

FedBalancer: Data and Pace Control for Efficient Federated Learning on Heterogeneous Clients

Jaemin Shin, Yuanchun Li, Yunxin Liu +1

Federated Learning (FL) trains a machine learning model on distributed clients without exposing individual data. Unlike centralized training that is usually based on carefully-orga…