张凯｜上海电力大学｜学者主页

期刊论文

2026

联邦学习中的阶段感知型差分隐私安全保护

李雷，张凯，陈志浩，仲崇理，李明昊

《计算机工程与设计》

DOI

2025

数据出境安全风险监测预警关键技术综述

张凯，时金桥，马乐乐，郭晓威，刁毅刚，李凤华

《通信学报》

2023

国家信息安全治理体系和治理能力现代化建设面临的挑战

张凯，黄培，方靖雯

《情报杂志》，Vol. 42, No. 4

下载原文

2023

大数据安全治理与防范——反欺诈体系建设

张凯

《人民邮电出版社》

2019

高校数据安全治理实践

赵洁，张凯，田鹏

《网络空间安全》

2018

基于密钥状态散列树的密钥存储管理方案

王祥宇，马建峰，苗银宾，张凯，伍祈应

《通信学报》

2018

在线/离线的可追责属性加密方案

张凯，马建峰，张俊伟，应作斌，张涛，刘西蒙

《计算机研究与发展》

2017

支持高效撤销的多机构属性加密方案

张凯，马建峰，李辉，张俊伟，张涛

《通信学报》

2016

具备强表达能力的选择密文安全高效属性基加密方案

张凯，魏立斐，李祥学，陈洁，钱海峰

《计算机研究与发展》

会议论文

2024

人工智能安全风险及其全球治理

蔡晶晶，陈俊，张凯，付磊

《2024世界智能产业博览会人工智能安全治理主题论坛论文集》

DOI

预印本

2026

MOSAIC: Composable Safety Alignment with Modular Control Tokens

Jingyu Peng, Hongyu Chen, Jiancheng Dong, Maolin Wang, Wenxi Li, Yuchen Li, Kai Zhang, Xiangyu Zhao

arXiv preprint

2025

Response-Based Knowledge Distillation for Multilingual Jailbreak Prevention Unwittingly Compromises Safety

Max Zhang, Derek Liu, Kai Zhang, Joshua Franco, Haihao Liu

arXiv preprint

2025

Logic Jailbreak: Efficiently Unlocking LLM Safety Restrictions Through Formal Logical Expression

Jingyu Peng, Maolin Wang, Nan Wang, Jiatong Li, Yuchen Li, Yuyang Ye, Wanyu Wang, Pengyue Jia, Kai Zhang, Xiangyu Zhao

arXiv preprint

2024

Privacy-preserved LLM Cascade via CoT-enhanced Policy Learning

Kai Zhang, Congchao Wang, Liqian Peng, Alec Go, Xiaozhong Liu

arXiv preprint

2023

Bounded and Unbiased Composite Differential Privacy

Kai Zhang, Yanjun Zhang, Ruoxi Sun, Pei-Wei Tsai, Muneeb Ul Hassan, Xin Yuan, Minhui Xue, Jinjun Chen

arXiv preprint

2023

Backdoor Attacks to Pre-trained Unified Foundation Models

Zenghui Yuan, Yixin Liu, Kai Zhang, Pan Zhou, Lichao Sun

arXiv preprint

2023

Sensitive Data Detection with High-Throughput Machine Learning Models in Electrical Health Records

Kai Zhang, Xiaoqian Jiang

arXiv preprint

2023

FedSecurity: Benchmarking Attacks and Defenses in Federated Learning and Federated LLMs

Shanshan Han, Baturalp Buyukates, Zijian Hu, Han Jin, Weizhao Jin, Lichao Sun, Xiaoyang Wang, Wenxuan Wu, Chulin Xie, Yuhang Yao, Kai Zhang, Qifan Zhang, Yuhui Zhang, Carlee Joe-Wong, Salman Avestimehr, Chaoyang He

arXiv preprint

2022

Efficient Federated Learning on Knowledge Graphs via Privacy-preserving Relation Embedding Aggregation

Kai Zhang, Yu Wang, Hongyi Wang, Lifu Huang, Carl Yang, Xun Chen, Lichao Sun

arXiv preprint

2021

Learning to Detect: A Data-driven Approach for Network Intrusion Detection

Zachary Tauscher, Yushan Jiang, Kai Zhang, Jian Wang, Houbing Song

arXiv preprint

张凯

精选作品

期刊论文

联邦学习中的阶段感知型差分隐私安全保护

数据出境安全风险监测预警关键技术综述

国家信息安全治理体系和治理能力现代化建设面临的挑战

大数据安全治理与防范——反欺诈体系建设

高校数据安全治理实践

基于密钥状态散列树的密钥存储管理方案

在线/离线的可追责属性加密方案

支持高效撤销的多机构属性加密方案

具备强表达能力的选择密文安全高效属性基加密方案

会议论文

人工智能安全风险及其全球治理

预印本

MOSAIC: Composable Safety Alignment with Modular Control Tokens

Response-Based Knowledge Distillation for Multilingual Jailbreak Prevention Unwittingly Compromises Safety

Logic Jailbreak: Efficiently Unlocking LLM Safety Restrictions Through Formal Logical Expression

Privacy-preserved LLM Cascade via CoT-enhanced Policy Learning

Bounded and Unbiased Composite Differential Privacy

Backdoor Attacks to Pre-trained Unified Foundation Models

Sensitive Data Detection with High-Throughput Machine Learning Models in Electrical Health Records

FedSecurity: Benchmarking Attacks and Defenses in Federated Learning and Federated LLMs

Efficient Federated Learning on Knowledge Graphs via Privacy-preserving Relation Embedding Aggregation

Learning to Detect: A Data-driven Approach for Network Intrusion Detection

研究方向