3 papers
cs.CV2025
StegaVAR: Privacy-Preserving Video Action Recognition via Steganographic Domain Analysis
Lixin Chen, Chaomeng Chen, Jiale Zhou +2
Despite the rapid progress of deep learning in video action recognition (VAR) in recent years, privacy leakage in videos remains a critical concern. Current state-of-the-art privac…
cs.CL2025
SMEC: Rethinking Matryoshka Representation Learning for Retrieval Embedding Compression
Biao Zhang, Lixin Chen, Tong Liu +1
Large language models (LLMs) generate high-dimensional embeddings that capture rich semantic and syntactic information. However, high-dimensional embeddings exacerbate computationa…
cs.LG2024
How Does the Smoothness Approximation Method Facilitate Generalization for Federated Adversarial Learning?
Wenjun Ding, Ying An, Lixing Chen +3
Federated Adversarial Learning (FAL) is a robust framework for resisting adversarial attacks on federated learning. Although some FAL studies have developed efficient algorithms, t…