activity
20242026
most citedBoBa: Boosting Backdoor Detection through Data Distribution Inference in Federated Learning

2 citations · 2 across the 4 of their papers we have counts for

collaborators

8 papers

cs.LG2026

The Devil is in the Condition Numbers: Why is GLU Better than non-GLU Structure?

Xingyu Lyu, Qianqian Xu, Zhiyong Yang +2

Gated Linear Units (GLU) and their variants are widely adopted in modern open-source large language model architectures and consistently outperform their non-gated counterparts, ye…

cs.IR2026

ALDEN: Boosting Private Data Extraction from Retrieval-Augmented Generation Systems via Active Learning and Distribution Estimation

Xingyu Lyu, Jianfeng He, Ning Wang +5

Retrieval-Augmented Generation (RAG) is widely used to augment large language models with external knowledge retrieval to improve reliability and generalization. However, recent st…

cs.CR2026

ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying

Xingyu Lyu, Jianfeng He, Ning Wang +5

Large Language Model (LLM) agents have achieved rapid adoption and demonstrated remarkable capabilities across a wide range of applications. To improve reasoning and task execution…

cs.LG20262 cited

BoBa: Boosting Backdoor Detection through Data Distribution Inference in Federated Learning

Zhengyuan Jiang, Xingyu Lyu, Shanghao Shi +5

Federated learning, while being a promising approach for collaborative model training, is susceptible to backdoor attacks due to its decentralized nature. Backdoor attacks have sho…

cs.CR2025

Buffer is All You Need: Defending Federated Learning against Backdoor Attacks under Non-iids via Buffering

Xingyu Lyu, Ning Wang, Yang Xiao +4

Federated Learning (FL) is a popular paradigm enabling clients to jointly train a global model without sharing raw data. However, FL is known to be vulnerable towards backdoor atta…

cs.CR2025

Demystifying Private Transactions and Their Impact in PoW and PoS Ethereum

Xingyu Lyu, Mengya Zhang, Xiaokuan Zhang +3

In Ethereum, private transactions, a specialized transaction type employed to evade public Peer-to-Peer (P2P) network broadcasting, remain largely unexplored, particularly in the c…