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
Shengfang Zhai — most-cited papers & profile · Cybersecurity
← authors
·
overview
Shengfang Zhai
11
papers ·
20
citations
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
NCL: Textual Backdoor Defense Using Noise-augmented Contrastive Learning
2023 · 11 citations
GuardReasoner: Towards Reasoning-based LLM Safeguards
2025 · 2 citations
Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoning
2023 · 2 citations
BadDLM: Backdooring Diffusion Language Models with Diverse Targets
2026
MemPot: Defending Against Memory Extraction Attack with Optimized Honeypots
2026
Efficient Input-level Backdoor Defense on Text-to-Image Synthesis via Neuron Activation Variation
2025
Life-Cycle Routing Vulnerabilities of LLM Router
2025
Kallima: A Clean-label Framework for Textual Backdoor Attacks
2022
Top co-authors
Qingni Shen
· 5
Yinpeng Dong
· 5
Jiaheng Zhang
· 4
Xiaoyang Ji
· 2
Yue Liu
· 2
Bryan Hooi
· 1
Cong Li
· 1
Guanghao Jin
· 1
Hang Su
· 1
Haoran Gao
· 1
Hongcheng Gao
· 1
Huanran Chen
· 1
Topics
Adversarial ML
Vulnerability Detection
Threat Intelligence
LLM Security
Network Security