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
Peter Garraghan — most-cited papers & profile · Cybersecurity
← authors
·
overview
Peter Garraghan
4
papers ·
4
citations ·
18
h-index
Lancaster University
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
Model Leeching: An Extraction Attack Targeting LLMs
2023 · 4 citations
Behind the Refusal: Determining Guardrail Activation via Behavioral Monitoring
2026
kNNGuard: Turning LLM Hidden Activations into a Training-Free Configurable Guardrail
2026
kNNGuard: Turning LLM Hidden Activations into a Training-Free Configurable Guardrail
2026
Topics
Evaluation
Safety
Benchmarks
Efficiency
Fine-Tuning
Safety & Alignment
Training Techniques