Edoardo Debenedetti
- Papers
- 5
Cite
Notes
Only stored in your browser.
5papers
Authored papers
5Defeating Prompt Injections by Design
arXiv 2025
JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
arXiv 2024
AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
arXiv 2024
Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition
arXiv 2024
Evading Black-box Classifiers Without Breaking Eggs
arXiv 2023
Affiliations
No known affiliations.
Frequent co-authors
10from 5 papers