Awesome Cybersecurity
📄
Papers
🧭
Topics
🔥
Trending
🗺️
Map
🏆
Leaderboards
🎓
Learn
🤖
Ask AI
⋯
More
👥
Authors
📚
Reading Packs
📊
Datasets
🛠️
Tools
📰
News
📝
Blogs
✉️
Newsletter
🎯
Research Radar
🔖
Saved
+ Add Paper
☾
☀
← authors
·
overview
Loading author…
🤖
Ask AI
Xuanli He — most-cited papers & profile · Cybersecurity
← authors
·
overview
Xuanli He
15
papers ·
213
citations ·
13
h-index
University College London
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
Mitigating Backdoor Poisoning Attacks Through The Lens Of Spurious Correlation
2023 · 7 citations
Student Surpasses Teacher: Imitation Attack for Black-Box NLP APIs
2021 · 5 citations
SEEP: Training Dynamics Grounds Latent Representation Search For Mitigating Backdoor Poisoning Attacks
2024 · 3 citations
Killing One Bird with Two Stones: Model Extraction and Attribute Inference Attacks against BERT-based APIs
2021 · 2 citations
Attacks on Third-Party APIs of Large Language Models
2024 · 2 citations
Defending against Backdoor Attacks via Module Switching
2025
Tuba: Cross-lingual Transferability Of Backdoor Attacks In Llms With Instruction Tuning
2024
Cut The Deadwood Out: Backdoor Purification Via Guided Module Substitution
2024
Top co-authors
Qiongkai Xu
· 6
Jun Wang
· 3
Lingjuan Lyu
· 2
Weijun Li
· 2
Chen Chen
· 1
Fangzhao Wu
· 1
Gholamreza Haffari
· 1
Lizhen Qu
· 1
Mark Dras
· 1
Wanru Zhao
· 1
Yao Tong
· 1
Topics
Adversarial ML
cs.CR
Vulnerability Detection
LLM Security
Privacy
Threat Intelligence
Anomaly Detection