刘洋｜上海大学｜学者主页

2026

基于加权知识图谱的交互式智能导诊系统研究

李潘，刘洋，王钦

《情报理论与实践》，Vol. 49, No. 8

下载原文

2026

基于深度学习的物联网多源数据时序异常检测方法

刘洋，赵少锋

《物联网技术》

2024

ESB-FL: Efficient and Secure Blockchain-Based Federated Learning With Fair Payment

Biwen Chen, Honghong Zeng, Tao Xiang, Shangwei Guo, Tian-Wei Zhang, Yang Liu

IEEE Transactions on Big Data

DOI

2023

Automatic Transformation Search Against Deep Leakage From Gradients

Wei Gao, Xu Zhang, Shangwei Guo, Tian-Wei Zhang, Tao Xiang, Han Qiu, Yonggang Wen, Yang Liu

IEEE Transactions on Pattern Analysis and Machine Intelligence

DOI

2023

MASTERKEY: Automated Jailbreaking of Large Language Model Chatbots

Ge-Lei Deng, Yi Liu, Yuekang Li, Kailong Wang, Ying Zhang, Zefeng Li, Hao-Yu Wang, Tian-Wei Zhang, Yang Liu

Network and Distributed System Security Symposium

DOI

2023

NAUTILUS: Automated RESTful API Vulnerability Detection

Ge-Lei Deng, Zhiyi Zhang, Yuekang Li, Yi Liu, Tian-Wei Zhang, Yang Liu, Guo Yu, Dongjin Wang

USENIX Security Symposium

2023

PentestGPT: An LLM-empowered Automatic Penetration Testing Tool

Ge-Lei Deng, Yi Liu, V'ictor Mayoral-Vilches, Peng Liu, Yuekang Li, Yuan Xu, Tian-Wei Zhang, Yang Liu, M. Pinzger, S. Rass

arXiv.org

DOI

2023

Multi-target Backdoor Attacks for Code Pre-trained Models

Yanzhou Li, Shang-Qing Liu, Kangjie Chen, Xiao-Fei Xie, Tian-Wei Zhang, Yang Liu

Annual Meeting of the Association for Computational Linguistics

DOI

2023

Prompt Injection attack against LLM-integrated Applications

Yi Liu, Ge-Lei Deng, Yuekang Li, Kailong Wang, Tian-Wei Zhang, Yepang Liu, Hao-Yu Wang, Yanhong Zheng, Yang Liu

arXiv.org

DOI

2023

ADS-Lead: Lifelong Anomaly Detection in Autonomous Driving Systems

Xing-Shuo Han, Yuan Zhou, Kangjie Chen, Han Qiu, Mei-Kang Qiu, Yang Liu, Tian-Wei Zhang

IEEE transactions on intelligent transportation systems (Print)

DOI

2022

On the (In)Security of Secure ROS2

Ge-Lei Deng, Guowen Xu, Yuan Zhou, Tian-Wei Zhang, Yang Liu

Conference on Computer and Communications Security

DOI

2022

A Formal Methodology for Verifying Side-Channel Vulnerabilities in Cache Architectures

Ke-Qing Jiang, Tian-Wei Zhang, David Sanán, Yong-Wang Zhao, Yang Liu

IEEE International Conference on Formal Engineering Methods

DOI

2022

SoK: Rethinking Sensor Spoofing Attacks against Robotic Vehicles from a Systematic View

Yuan Xu, Xing-Shuo Han, Ge-Lei Deng, Ji-Wei Li, Yang Liu, Tian-Wei Zhang

European Symposium on Security and Privacy

DOI

2021

Robust and Privacy-Preserving Collaborative Learning: A Comprehensive Survey

Shangwei Guo, Xu Zhang, Feiyu Yang, Tian-Wei Zhang, Yan Gan, Tao Xiang, Yang Liu

arXiv.org

2021

Systematic Testing of Autonomous Driving Systems Using Map Topology-Based Scenario Classification

Yun Tang, Yuan Zhou, Tianwei Zhang, Fenghua Wu, Yang Liu, Gang Wang

International Conference on Automated Software Engineering

DOI

2021

Temporal Watermarks for Deep Reinforcement Learning Models

Kangjie Chen, Shangwei Guo, Tian-Wei Zhang, Shu-Xin Li, Yang Liu

Adaptive Agents and Multi-Agent Systems

DOI

2021

An Investigation of Byzantine Threats in Multi-Robot Systems

Ge-Lei Deng, Yuan Zhou, Yuan Xu, Tian-Wei Zhang, Yang Liu

International Symposium on Recent Advances in Intrusion Detection

DOI

2021

A Unified Anomaly Detection Methodology for Lane-Following of Autonomous Driving Systems

Xing-Shuo Han, Kangjie Chen, Yuan Zhou, Mei-Kang Qiu, Chun Fan, Yang Liu, Tian-Wei Zhang

2021 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom)

DOI

2021

When NAS Meets Watermarking: Ownership Verification of DNN Models via Cache Side Channels

Xiaoxuan Lou, Shangwei Guo, Tian-Wei Zhang, Yinqian Zhang, Yang Liu

arXiv.org

2020

Fine-tuning Is Not Enough: A Simple yet Effective Watermark Removal Attack for DNN Models

Shangwei Guo, Tian-Wei Zhang, Han Qiu, Yi Zeng, Tao Xiang, Yang Liu

International Joint Conference on Artificial Intelligence

DOI

2020

Differentially Private Decentralized Learning

Shangwei Guo, Tian-Wei Zhang, Tao Xiang, Yang Liu

arXiv.org

2020

Privacy-preserving Collaborative Learning with Automatic Transformation Search

Wei Gao, Shangwei Guo, Tian-Wei Zhang, Han Qiu, Yong-Gang Wen, Yang Liu

Computer Vision and Pattern Recognition

DOI

2020

Stealing Deep Reinforcement Learning Models for Fun and Profit

Kangjie Chen, Shang-Wei Guo, Tian-Wei Zhang, Xiao-Fei Xie, Yang Liu

ACM Asia Conference on Computer and Communications Security

DOI

2020

Byzantine-Resilient Decentralized Stochastic Gradient Descent

Shangwei Guo, Tian-Wei Zhang, Han-Zhou Yu, Xiao-Fei Xie, L. Ma, Tao Xiang, Yang Liu

IEEE transactions on circuits and systems for video technology (Print)

DOI

2020

Topology-Aware Differential Privacy for Decentralized Image Classification

Shangwei Guo, Tian-Wei Zhang, Guowen Xu, Han-Zhou Yu, Tao Xiang, Yang Liu

IEEE transactions on circuits and systems for video technology (Print)

DOI

2020

The Hidden Vulnerability of Watermarking for Deep Neural Networks

Shangwei Guo, Tian-Wei Zhang, Han Qiu, Yi Zeng, Tao Xiang, Yang Liu

arXiv.org

刘洋

精选作品

期刊论文

基于加权知识图谱的交互式智能导诊系统研究

基于深度学习的物联网多源数据时序异常检测方法

ESB-FL: Efficient and Secure Blockchain-Based Federated Learning With Fair Payment

Automatic Transformation Search Against Deep Leakage From Gradients

MASTERKEY: Automated Jailbreaking of Large Language Model Chatbots

NAUTILUS: Automated RESTful API Vulnerability Detection

PentestGPT: An LLM-empowered Automatic Penetration Testing Tool

Multi-target Backdoor Attacks for Code Pre-trained Models

Prompt Injection attack against LLM-integrated Applications

ADS-Lead: Lifelong Anomaly Detection in Autonomous Driving Systems

On the (In)Security of Secure ROS2

A Formal Methodology for Verifying Side-Channel Vulnerabilities in Cache Architectures

SoK: Rethinking Sensor Spoofing Attacks against Robotic Vehicles from a Systematic View

Robust and Privacy-Preserving Collaborative Learning: A Comprehensive Survey

Systematic Testing of Autonomous Driving Systems Using Map Topology-Based Scenario Classification

Temporal Watermarks for Deep Reinforcement Learning Models

An Investigation of Byzantine Threats in Multi-Robot Systems

A Unified Anomaly Detection Methodology for Lane-Following of Autonomous Driving Systems

When NAS Meets Watermarking: Ownership Verification of DNN Models via Cache Side Channels

Fine-tuning Is Not Enough: A Simple yet Effective Watermark Removal Attack for DNN Models

Differentially Private Decentralized Learning

Privacy-preserving Collaborative Learning with Automatic Transformation Search

Stealing Deep Reinforcement Learning Models for Fun and Profit

Byzantine-Resilient Decentralized Stochastic Gradient Descent

Topology-Aware Differential Privacy for Decentralized Image Classification

The Hidden Vulnerability of Watermarking for Deep Neural Networks

预印本

PackVFL: Efficient HE Packing for Vertical Federated Learning

Practical and Secure Federated Recommendation with Personalized Masks

Differentially Private Linear Regression over Fully Decentralized Datasets

研究方向