Yang Zhang

Detecting Compromised Email Accounts from the Perspective of Graph Topology

2016

While email plays a growingly important role on the Internet, we are faced with more severe challenges brought by compromised email accounts, especially for the administrators of institutional email service providers. Inspired by the previous …

Model-Based Minimum Privacy Disclosure Recommendation for Authorization Policies

2016

This paper presents a privacy disclosure recommendation approach based on a privacy cost model. The approach involves selecting appropriate credentials or attributes from users, and automatically building a new credential to fulfill service's authorization policies. …

Knowledge-Learning Service Construction Based on Events

2016

Automatically constructing a composite service from a set of basic services is not desirable in practice because the composition assumption often over-simplifies the realistic constraints and states. We try to propose a stepwise methodology to …

Structure design for prediction system of radar electromagnetic environment on dynamic battlefield

2016

The prediction system of radar electromagnetic environment on dynamic battlefield helps people full understand the effect of external radar electromagnetic to combat action in different war situations. Thereby electronic information arm system can be used …

Syntax-Based Chinese-Vietnamese Tree-to-Tree Statistical Machine Translation with Bilingual Features

2019 · ACM Transactions on Asian and Low-Resource Language Information Processing

Because of the scarcity of bilingual corpora, current Chinese--Vietnamese machine translation is far from satisfactory. Considering the differences between Chinese and Vietnamese, we investigate whether linguistic differences can be used to supervise machine translation and …

Stronger uncertainty relations with improvable upper and lower bounds

2016 · arXiv (Cornell University)

We utilize quantum superposition principle to establish the improvable upper and lower bounds on the stronger uncertainty relation, i.e., the "weighted-like" sum of the variances of observables. Our bounds include some free parameters which not …

Tiered cloud storage via two-stage, latency-aware bidding

2017 · arXiv (Cornell University)

In cloud storage, the digital data is stored in logical storage pools, backed by heterogeneous physical storage media and computing infrastructure that are managed by a Cloud Service Provider (CSP). To balance the tradeoff between …

Circuit QED: Cross-Kerr-effect induced by a superconducting qutrit without classical pulses

2016 · arXiv (Cornell University)

The realization of cross-Kerr nonlinearity is an important task for many applications in quantum information processing. In this work, we propose a method for realizing cross-Kerr nonlinearity interaction between two superconducting coplanar waveguide resonators coupled …

A Game Theoretic Approach to Class-wise Selective Rationalization.

2019 · DSpace@MIT (Massachusetts Institute of Technology)

Selection of input features such as relevant pieces of text has become a common technique of highlighting how complex neural predictors operate. The selection can be optimized post-hoc for trained models or incorporated directly into …

Towards Plausible Graph Anonymization

2017 · SERVAL (Université de Lausanne)

Social graphs derived from online social interactions contain a wealth of information that is nowadays extensively used by both industry and academia. However, as social graphs contain sensitive information, they need to be properly anonymized …

Characterizing the Occurrence of Dockerfile Smells in Open-Source Software: An Empirical Study

2020 · IEEE Access

Dockerfile plays an important role in the Docker-based software development process, but many Dockerfile codes are infected with smells in practice. Understanding the occurrence of Dockerfile smells in open-source software can benefit the practice of …

Towards Plausible Graph Anonymization

2020

Social graphs derived from online social interactions contain a wealth of information that is nowadays extensively used by both industry and academia. However, as social graphs contain sensitive information, they need to be properly anonymized …

A Unified Sequence-to-Sequence Front-End Model for Mandarin Text-to-Speech Synthesis

2020

In Mandarin text-to-speech (TTS) system, the front-end text processing module significantly influences the intelligibility and naturalness of synthesized speech. Building a typical pipeline-based front-end which consists of multiple individual components requires extensive efforts. In this …

BAAAN: Backdoor Attacks Against Autoencoder and GAN-Based Machine Learning Models

2020 · arXiv (Cornell University)

The tremendous progress of autoencoders and generative adversarial networks (GANs) has led to their application to multiple critical tasks, such as fraud detection and sanitized data generation. This increasing adoption has fostered the study of …

Model Stealing Attacks Against Inductive Graph Neural Networks

2022 · 2022 IEEE Symposium on Security and Privacy (SP)

Many real-world data come in the form of graphs. Graph neural networks (GNNs), a new family of machine learning (ML) models, have been proposed to fully leverage graph data to build powerful applications. In particular, …

Applications of Multi-Agent Reinforcement Learning in Future Internet: A Comprehensive Survey

2022 · IEEE Communications Surveys & Tutorials

Future Internet involves several emerging technologies such as 5G and beyond 5G networks, vehicular networks, unmanned aerial vehicle (UAV) networks, and Internet of Things (IoTs). Moreover, the future Internet becomes heterogeneous and decentralized with a …

How to Retrain Recommender System?

2020

Practical recommender systems need be periodically retrained to refresh the model with new interaction data. To pursue high model fidelity, it is usually desirable to retrain the model on both historical and new data, since …

Get a Model! Model Hijacking Attack Against Machine Learning Models

2021 · arXiv (Cornell University)

Machine learning (ML) has established itself as a cornerstone for various critical applications ranging from autonomous driving to authentication systems. However, with this increasing adoption rate of machine learning models, multiple attacks have emerged. One …

Backdoor Attacks Against Dataset Distillation

2023

Dataset distillation has emerged as a prominent technique to improve data efficiency when training machine learning models. It encapsulates the knowledge from a large dataset into a smaller synthetic dataset. A model trained on this …

In ChatGPT We Trust? Measuring and Characterizing the Reliability of ChatGPT

2023 · arXiv (Cornell University)

The way users acquire information is undergoing a paradigm shift with the advent of ChatGPT. Unlike conventional search engines, ChatGPT retrieves knowledge from the model itself and generates answers for users. ChatGPT's impressive question-answering (QA) …

NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models

2023 · arXiv (Cornell University)

Prompt-based learning is vulnerable to backdoor attacks. Existing backdoor attacks against prompt-based models consider injecting backdoors into the entire embedding layers or word embedding vectors. Such attacks can be easily affected by retraining on downstream …

Prediction then Correction: An Abductive Prediction Correction Method for Sequential Recommendation

2023

Sequential recommender models typically generate predictions in a single step during testing, without considering additional prediction correction to enhance performance as humans would. To improve the accuracy of these models, some researchers have attempted to …

Hybrid Data Augmentation for Citation Function Classification

2023

The citation function generally signifies the purpose or reason underlying a citation within a scholarly paper or a research article. Automatic citation function classification is, therefore, a task in computational linguistics and information science that …

From Generative AI to Generative Internet of Things: Fundamentals, Framework, and Outlooks

2023 · arXiv (Cornell University)

Generative Artificial Intelligence (GAI) possesses the capabilities of generating realistic data and facilitating advanced decision-making. By integrating GAI into modern Internet of Things (IoT), Generative Internet of Things (GIoT) is emerging and holds immense potential …

NL2TL: Transforming Natural Languages to Temporal Logics using Large Language Models

2023

Temporal Logic (TL) can be used to rigorously specify complex high-level specification for systems in many engineering applications. The translation between natural language (NL) and TL has been under-explored due to the lack of dataset …

Exact Spin Correlators of Integrable Quantum Circuits from Algebraic Geometry

2024 · arXiv (Cornell University)

We calculate the correlation functions of strings of spin operators for integrable quantum circuits exactly. These observables can be used for calibration of quantum simulation platforms. We use algebraic Bethe Ansatz, in combination with computational …

FAKEPCD: Fake Point Cloud Detection via Source Attribution

2024

To prevent the mischievous use of synthetic (fake) point clouds produced by generative models, we pioneer the study of detecting point cloud authenticity and attributing them to their sources. We propose an attribution framework FakePCD …

A Parallel Tempering Processing Architecture with Multi-Spin Update for Fully-Connected Ising Models

2024

Combinatorial optimization problems (COPs) are notoriously difficult to solve for classic Von-Neumann computers, which are ubiquitous in various domains. As a state-of-the-art hardware acceleration scheme for COPs, Ising machines are one of the promising research …

Causality-Enhanced Behavior Sequence Modeling in LLMs for Personalized Recommendation

2024 · arXiv (Cornell University)

Recent advancements in recommender systems have focused on leveraging Large Language Models (LLMs) to improve user preference modeling, yielding promising outcomes. However, current LLM-based approaches struggle to fully leverage user behavior sequences, resulting in suboptimal …

ExClique: An Express Consensus Algorithm for High-Speed Transaction Process in Blockchains

2025 · arXiv (Cornell University)

Proof of Authority (PoA) plays a pivotal role in blockchains for reaching consensus. Clique, which selects consensus nodes to generate blocks with a pre-determined order, is the most popular implementation of PoA due to its …

Data Duplication: A Novel Multi-Purpose Attack Paradigm in Machine Unlearning

2025 · arXiv (Cornell University)

Duplication is a prevalent issue within datasets. Existing research has demonstrated that the presence of duplicated data in training datasets can significantly influence both model performance and data privacy. However, the impact of data duplication …

Intelligent detection and recovery on satellite telemetry loss

2025 · Journal of Physics Conference Series

Abstract The article takes the high-orbit satellite telemetry system as an example. Firstly, the general system architecture of the satellite telemetry system is summarized. Then, starting from the system design characteristics, the recovery strategy analysis …

Stain Normalization of Histopathological Images Based on Deep Learning: A Review

2025 · Diagnostics

Histopathological images stained with hematoxylin and eosin (H&E) are crucial for cancer diagnosis and prognosis. However, color variations caused by differences in tissue preparation and scanning devices can lead to data distribution discrepancies, adversely affecting …

Revisiting Multi-Agent World Modeling from a Diffusion-Inspired Perspective

2025

World models have recently attracted growing interest in Multi-Agent Reinforcement Learning (MARL) due to their ability to improve sample efficiency for policy learning. However, accurately modeling environments in MARL is challenging due to the exponentially …

Code-as-Symbolic-Planner: Foundation Model-Based Robot Planning via Symbolic Code Generation

2025 · arXiv (Cornell University)

Recent works have shown great potentials of Large Language Models (LLMs) in robot task and motion planning (TAMP). Current LLM approaches generate text- or code-based reasoning chains with sub-goals and action plans. However, they do …

Streaming Recommender Systems

2017

The increasing popularity of real-world recommender systems produces data continuously and rapidly, and it becomes more realistic to study recommender systems under streaming scenarios. Data streams present distinct properties such as temporally ordered, continuous and …

Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control

2019

Mo Yu, Shiyu Chang, Yang Zhang, Tommi Jaakkola. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Causal Intervention for Leveraging Popularity Bias in Recommendation

2021

Recommender system usually faces popularity bias issues: from the data perspective, items exhibit uneven (usually long-tail) distribution on the interaction frequency; from the method perspective, collaborative filtering methods are prone to amplify the bias by …

TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation

2023

Large Language Models (LLMs) have demonstrated remarkable performance across diverse domains, thereby prompting researchers to explore their potential for use in recommendation systems. Initial attempts have leveraged the exceptional capabilities of LLMs, such as rich …