Zheng Lin

Marginal Utility Diminishes: Exploring the Minimum Knowledge for BERT Knowledge Distillation

2021 · arXiv (Cornell University)

Recently, knowledge distillation (KD) has shown great success in BERT compression. Instead of only learning from the teacher's soft label as in conventional KD, researchers find that the rich information contained in the hidden layers …

Attentive Multi-Layer Perceptron for Non-autoregressive Generation

2023 · arXiv (Cornell University)

Autoregressive~(AR) generation almost dominates sequence generation for its efficacy. Recently, non-autoregressive~(NAR) generation gains increasing popularity for its efficiency and growing efficacy. However, its efficiency is still bottlenecked by quadratic complexity in sequence lengths, which is …

Efficient Parallel Split Learning Over Resource-Constrained Wireless Edge Networks

2024 · IEEE Transactions on Mobile Computing

The increasingly deeper neural networks hinder the democratization of privacy-enhancing distributed learning, such as federated learning (FL), to resource-constrained devices. To overcome this challenge, in this paper, we advocate the integration of edge computing paradigm …

DP-TRAE: A Dual-Phase Merging Transferable Reversible Adversarial Example for Image Privacy Protection

2025

In the field of digital security, Reversible Adversarial Examples (RAE) combine adversarial attacks with reversible data hiding techniques to effectively protect sensitive data and prevent unauthorized analysis by malicious Deep Neural Networks (DNNs). However, existing …

PIG: Privacy Jailbreak Attack on LLMs via Gradient-based Iterative In-Context Optimization

2025 · arXiv (Cornell University)

Large Language Models (LLMs) excel in various domains but pose inherent privacy risks. Existing methods to evaluate privacy leakage in LLMs often use memorized prefixes or simple instructions to extract data, both of which well-alignment …

HASFL: Heterogeneity-aware Split Federated Learning over Edge Computing Systems

2025 · arXiv (Cornell University)

Split federated learning (SFL) has emerged as a promising paradigm to democratize machine learning (ML) on edge devices by enabling layer-wise model partitioning. However, existing SFL approaches suffer significantly from the straggler effect due to …