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
Tsung-Yi Ho — most-cited papers & profile · Cybersecurity
← authors
·
overview
Tsung-Yi Ho
10
papers ·
38
citations ·
42
h-index
Chinese University of Hong Kong · University of Hong Kong
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models
2023 · 5 citations
Defensive Prompt Patch: A Robust and Interpretable Defense of LLMs against Jailbreak Attacks
2024 · 3 citations
Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift
2023 · 2 citations
Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes
2024 · 2 citations
Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models
2024
Top co-authors
Pin-Yu Chen
· 4
Sheng-Yen Chou
· 2
Chen Xiong
· 1
Guangyu Shen
· 1
Guanhong Tao
· 1
Kaiyuan Zhang
· 1
Pin‐Yu Chen
· 1
Qiuling Xu
· 1
Shengwei An
· 1
Shiqing Ma
· 1
Siyuan Cheng
· 1
Xiangyu Qi
· 1
Topics
Adversarial ML
Vulnerability Detection
LLM Security
Threat Intelligence