Picture for Edoardo Debenedetti

Edoardo Debenedetti

Defeating Prompt Injections by Design

Add code
Mar 24, 2025
Viaarxiv icon

AutoAdvExBench: Benchmarking autonomous exploitation of adversarial example defenses

Add code
Mar 03, 2025
Viaarxiv icon

Exploring Memorization and Copyright Violation in Frontier LLMs: A Study of the New York Times v. OpenAI 2023 Lawsuit

Add code
Dec 09, 2024
Viaarxiv icon

Measuring Non-Adversarial Reproduction of Training Data in Large Language Models

Add code
Nov 15, 2024
Viaarxiv icon

Adversarial Search Engine Optimization for Large Language Models

Add code
Jun 26, 2024
Figure 1 for Adversarial Search Engine Optimization for Large Language Models
Figure 2 for Adversarial Search Engine Optimization for Large Language Models
Figure 3 for Adversarial Search Engine Optimization for Large Language Models
Figure 4 for Adversarial Search Engine Optimization for Large Language Models
Viaarxiv icon

AgentDojo: A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents

Add code
Jun 19, 2024
Viaarxiv icon

Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition

Add code
Jun 12, 2024
Figure 1 for Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition
Figure 2 for Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition
Figure 3 for Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition
Figure 4 for Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition
Viaarxiv icon

AI Risk Management Should Incorporate Both Safety and Security

Add code
May 29, 2024
Figure 1 for AI Risk Management Should Incorporate Both Safety and Security
Viaarxiv icon

JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models

Add code
Mar 28, 2024
Figure 1 for JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
Figure 2 for JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
Figure 3 for JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
Figure 4 for JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
Viaarxiv icon

Scaling Compute Is Not All You Need for Adversarial Robustness

Add code
Dec 20, 2023
Viaarxiv icon