Get started
Author

Xinlei He

Stealing Links from Graph Neural Networks
2020 · He, Xinlei, Jia, Jinyuan, et al. · arXiv (Cornell University) · 86
PDF
DeepScan: Exploiting Deep Learning for Malicious Account Detection in Location-Based Social Networks
2018 · Qingyuan Gong, Yang Chen, et al. · IEEE Communications Magazine · 86
Model Stealing Attacks Against Inductive Graph Neural Networks
2022 · Yun Shen, Xinlei He, et al. · IEEE Symposium on Security and Privacy (S&P) · 80
PDF
Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models
2023 · Yiting Qu, Xinyue Shen, et al. · ACM SIGSAC Conference on Computer and Communications Security (CCS) · 76
Node-Level Membership Inference Attacks Against Graph Neural Networks
2021 · He, Xinlei, Wen, Rui, et al. · arXiv (Cornell University) · 56
PDF
MGTBench: Benchmarking Machine-Generated Text Detection
2024 · Xinlei He, Xinyue Shen, et al. · ACM SIGSAC Conference on Computer and Communications Security (CCS) · 45
PDF
You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content
2024 · Xinlei He, Savvas Zannettou, et al. · IEEE Symposium on Security and Privacy (S&P) · 39
DatingSec: Detecting Malicious Accounts in Dating Apps Using a Content-Based Attention Network
2021 · Xinlei He, Qingyuan Gong, et al. · IEEE Transactions on Dependable and Secure Computing · 38
SSLGuard
2022 · Tianshuo Cong, Xinlei He, et al. · ACM SIGSAC Conference on Computer and Communications Security (CCS) · 35
Quantifying and Mitigating Privacy Risks of Contrastive Learning
2021 · Xinlei He, Yang Zhang · ACM SIGSAC Conference on Computer and Communications Security (CCS) · 33
MGTBench: Benchmarking Machine-Generated Text Detection
2023 · He, Xinlei, Shen, Xinyue, et al. · arXiv (Cornell University) · 29
PDF
Auditing Membership Leakages of Multi-Exit Networks
2022 · Zheng Li, Yiyong Liu, et al. · ACM SIGSAC Conference on Computer and Communications Security (CCS) · 28
Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoders
2023 · Zeyang Sha, Xinlei He, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 24
Cross-site Prediction on Social Influence for Cold-start Users in Online Social Networks
2021 · Qingyuan Gong, Yang Chen, et al. · ACM Transactions on the Web · 23
PDF
Data Poisoning Attacks Against Multimodal Encoders
2022 · Yang, Ziqing, He, Xinlei, et al. · arXiv (Cornell University) · 21
PDF
Artificial intelligence security and privacy: a survey
2025 · Xinlei He, Guowen Xu, et al. · Science China Information Sciences · 20
PDF
On the Influence of Twitter Trolls during the 2016 US Presidential Election
2019 · Salamanos, Nikos, Jensen, Michael J., et al. · arXiv (Cornell University) · 19
PDF
On the Evolution of (Hateful) Memes by Means of Multimodal Contrastive Learning
2023 · Yiting Qu, Xinlei He, et al. · IEEE Symposium on Security and Privacy (S&P) · 17
PDF
PEFTGuard: Detecting Backdoor Attacks Against Parameter-Efficient Fine-Tuning
2025 · Zhen Sun, Tianshuo Cong, et al. · IEEE Symposium on Security and Privacy (S&P) · 14
PDF
On Xing Tian and the Perseverance of Anti-China Sentiment Online
2022 · Xinyue Shen, Xinlei He, et al. · Proceedings of the International AAAI Conference on Web and Social Media · 13
PDF
Jailbreak Attacks and Defenses Against Large Language Models: A Survey
2024 · Yi, Sibo, Liu, Yule, et al. · arXiv (Cornell University) · 12
PDF
Semi-Leak: Membership Inference Attacks Against Semi-supervised Learning
2022 · Xinlei He, Hongbin Liu, et al. · Lecture notes in computer science · 12
Trimming Mobile Applications for Bandwidth-Challenged Networks in Developing Regions
2021 · Qinge Xie, Qingyuan Gong, et al. · IEEE Transactions on Mobile Computing · 11
PDF
Are We in the AI-Generated Text World Already? Quantifying and Monitoring AIGT on Social Media
2025 · Zhen Sun, Zongmin Zhang, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting · 10
PDF
Membership-Doctor: Comprehensive Assessment of Membership Inference Against Machine Learning Models
2022 · He, Xinlei, Li, Zheng, et al. · arXiv (Cornell University) · 10
PDF
Works count: 152
Citation count: 980
H-index: 18
I10-index: 26
Year
Topic
Type