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
Daniel Kang — most-cited papers & profile · Cybersecurity
← authors
·
overview
Daniel Kang
17
papers ·
96
citations ·
24
h-index
University of Illinois Urbana-Champaign
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks
2023 · 27 citations
LLM Agents can Autonomously Exploit One-day Vulnerabilities
2024 · 12 citations
LLM Agents can Autonomously Hack Websites
2024 · 10 citations
CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities
2025 · 1 citations
Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents
2025
Top co-authors
Richard Fang
· 4
Akul Gupta
· 3
Qiusi Zhan
· 2
Rohan Bindu
· 2
Adarsh Danda
· 1
Antony Kellermann
· 1
Avi Dhir
· 1
Carlos Guestrin
· 1
Conner Jensen
· 1
Dylan Bowman
· 1
Eric Ihli
· 1
Henil Shalin Panchal
· 1
Topics
LLM Security
Vulnerability Detection
Threat Intelligence
Adversarial ML
Network Security