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
Stephen Casper — most-cited papers & profile · Cybersecurity
← authors
·
overview
Stephen Casper
10
papers ·
103
citations
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
Defending Against Unforeseen Failure Modes with Latent Adversarial Training
2024 · 2 citations
TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering
2026
Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities
2025
What Features in Prompts Jailbreak LLMs? Investigating the Mechanisms Behind Attacks
2024
Top co-authors
Dylan Hadfield-Menell
· 2
Bilal Chughtai
· 1
Constantin Weisser
· 1
Domenic Rosati
· 1
Furong Huang
· 1
Helen Yannakoudakis
· 1
Kellin Pelrine
· 1
Lennart Schulze
· 1
Oam Patel
· 1
Punya Syon Pandey
· 1
Robert Kirk
· 1
Saad Hossain
· 1
Topics
Adversarial ML
Vulnerability Detection
LLM Security