3 papers
cs.CR2024
RFLPA: A Robust Federated Learning Framework against Poisoning Attacks with Secure Aggregation
Peihua Mai, Ran Yan, Yan Pang
Federated learning (FL) allows multiple devices to train a model collaboratively without sharing their data. Despite its benefits, FL is vulnerable to privacy leakage and poisoning…
cs.CR2024
ConfusionPrompt: Practical Private Inference for Online Large Language Models
Peihua Mai, Youjia Yang, Ran Yan +2
State-of-the-art large language models (LLMs) are typically deployed as online services, requiring users to transmit detailed prompts to cloud servers. This raises significant priv…
cs.AI2023
Split-and-Denoise: Protect large language model inference with local differential privacy
Peihua Mai, Ran Yan, Zhe Huang +2
Large Language Models (LLMs) excel in natural language understanding by capturing hidden semantics in vector space. This process enriches the value of text embeddings for various d…