Yi Li

PrivPy: Enabling Scalable and General Privacy-Preserving Machine Learning

2018 · arXiv (Cornell University)

We introduce PrivPy, a practical privacy-preserving collaborative computation framework, especially optimized for machine learning tasks. PrivPy provides an easy-to-use and highly compatible Python programming front-end which supports high-level array operations and different secure computation engines …

An Innovative IPFS-Based Storage Model for Blockchain

2018

Blockchain technology has received great attention in recent years. However, the data volume of blockchain grows continuously due to the features that cannot be deleted and can only be added. Currently, the total size of …

PrivPy

2019

Privacy is a big hurdle for collaborative data mining across multiple parties. We present multi-party computation (MPC) framework designed for large-scale data mining tasks. PrivPy combines an easy-to-use and highly flexible Python programming interface with …

Pipeline Safety Early Warning Method for Distributed Signal using Bilinear CNN and LightGBM

2021

Oil and gas pipelines are known as the backbone of global energy, and securing their safety is crucial for energy supply. In this study, we utilized a novel machine learning method based on the spatiotemporal …

Improvement of image classification by multiple optical scattering

2021 · arXiv (Cornell University)

Multiple optical scattering occurs when light propagates in a non-uniform medium. During the multiple scattering, images were distorted and the spatial information they carried became scrambled. However, the image information is not lost but presents …

Effect of customer's perception on service robot acceptance

2021 · International Journal of Consumer Studies

Abstract A service robot is a physical entity integrated with information technology (IT) which can autonomously provide customized services to people. While the use of robots is regarded as one of the most important trends …

Research on a Virtual Machine Mode Transfer Method Supporting Energy Consumption Optimization

2022 · 2022 24th International Conference on Advanced Communication Technology (ICACT)

In traditional cloud resource optimization scheduling, excessive pursuit of service performance and system reliability has resulted in low utilization of system resources and severe energy dissipation. In this paper, transfer target of virtual machines was …

Integrating with Segmentation by Using Multi-Task Learning Improves Classification Performance in Medical Image Analysis

2022

Diagnosis of tumors is an important direction of computer-aided diagnosis (CAD). The shape, size, and boundary of the tumor are widely-used diagnostic evidence, and the corresponding segmentation annotated by the radiologists is a vital expert …

InvCon: A Dynamic Invariant Detector for Ethereum Smart Contracts

2022

Smart contracts are self-executing computer programs deployed on blockchain to enable trustworthy exchange of value without the need of a central authority. With the absence of documentation and specifications, routine tasks such as program understanding, …

Federated Graph Learning for EV Charging Demand Forecasting with Personalization Against Cyberattacks

2024 · arXiv (Cornell University)

Mitigating cybersecurity risk in electric vehicle (EV) charging demand forecasting plays a crucial role in the safe operation of collective EV chargings, the stability of the power grid, and the cost-effective infrastructure expansion. However, existing …

CORE4D: A 4D Human-Object-Human Interaction Dataset for Collaborative Object REarrangement

2024 · arXiv (Cornell University)

Understanding how humans cooperatively rearrange household objects is critical for VR/AR and human-robot interaction. However, in-depth studies on modeling these behaviors are under-researched due to the lack of relevant datasets. We fill this gap by …

Ground Pressure Hazard Monitoring and Early Warning in Complex Areas Research

2024 · Research Square

<title>Abstract</title> In order to solve the problems of MaKeng Iron Mine original ground pressure disaster prediction and warning indicators are single, the forecast accuracy is seriously insufficient, and there is a lack of intuitive on-line …

PAFedMIS: Personalized Asynchronous Federated Learning for Medical Image Segmentation

2025

As privacy protection gains momentum, federated learning has emerged as a cutting-edge approach in medical image analysis. However, the intricacies of medical image segmentation task have led to a dearth of research in this domain, …

Towards Robust Named Entity Recognition in Bangla With LLMs Based Data Augmentation

2024

Named Entity Recognition (NER) is a pivotal task in Natural Language Processing (NLP), focused on identifying specific entities in unstructured text. While significant advancements have been made, most existing methods are primarily designed for resource-rich …

Specification Mining for Smart Contracts with Trace Slicing and Predicate Abstraction

2025

Smart contracts are computer programs running on blockchains to implement Decentralized Applications. The absence of contract specifications hinders routine tasks, such as contract understanding and testing. In this work, we propose a specification mining approach …

SpecGen: Automated Generation of Formal Program Specifications via Large Language Models

2025

In the software development process, formal program specifications play a crucial role in various stages, including requirement analysis, software testing, and verification. However, manually crafting formal program specifications is rather difficult, making the job time-consuming …

<i>KeAD:</i> <i>K</i>nowledge-<i>e</i>nhanced Graph Attention Network for Accurate <i>A</i>nomaly <i>D</i>etection

2025 · IEEE Transactions on Services Computing

Anomaly detection has emerged as one of the core research topics to support workflow applications across various domains. To differentiate anomalies from underlying normal patterns of workflows, Graph Neural Networks (GNNs) models have been introduced. …

Leveraging Segment Anything Model for Source-Free Domain Adaptation via Dual Feature Guided Auto-Prompting

2025 · arXiv (Cornell University)

Source-free domain adaptation (SFDA) for segmentation aims at adapting a model trained in the source domain to perform well in the target domain with only the source model and unlabeled target data. Inspired by the …

PLaST: Towards Paralinguistic-aware Speech Translation

2026 · Proceedings of the AAAI Conference on Artificial Intelligence

Speech translation (ST) aims to translate speech from a source language into text in the target language. Naturally, speech signals contain paralinguistic cues beyond linguistic content, which could influence or even alter the interpretation of …