Wenyuan Xu

SPA

2015

More and more powerful personal smart devices take users, especially the elder, into a disaster of policy administration where users are forced to set personal management policies in these devices. Considering a real case of …

VarASV: Enabling Pitch-variable Automatic Speaker Verification via Multi-task Learning

2021 · 2021 IEEE 5th Conference on Energy Internet and Energy System Integration (EI2)

With the proliferation of voice assistants, using voice commands in Energy Internet becomes common practice, e.g., inspectors could control the substation inspection robot to perform automatic detection and information query by voice instructions. However, existing …

Oblivion: Poisoning Federated Learning by Inducing Catastrophic Forgetting

2023

Federated learning is exposed to model poisoning attacks as compromised clients may submit malicious model updates to pollute the global model. To defend against such attacks, robust aggregation rules are designed for the centralized server …

RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation

2024 · arXiv (Cornell University)

Large Language Models (LLMs) demonstrate human-level capabilities in dialogue, reasoning, and knowledge retention. However, even the most advanced LLMs face challenges such as hallucinations and real-time updating of their knowledge. Current research addresses this bottleneck …

BARBIE: Robust Backdoor Detection Based on Latent Separability

2025

Backdoor attacks are an essential risk to deep learning model sharing.Fundamentally, backdoored models are different from benign models considering latent separability, i.e., distinguishable differences in model latent representations.However, existing methods quantify latent separability by clustering …