dedeswim

Follow

Edoardo Debenedetti dedeswim

Follow

AI Security PhD Student @ethz-spylab | ETH Zurich | AI Agents Security | Prev Research Intern at Meta and Google

174 followers · 262 following

Achievements

Achievements

Highlights

Pro

Organizations

dedeswim/README.md

I am Edoardo, a CS PhD student at ETH Zürich, researching the security and privacy risks of ML in the real-world in the Secure and Private AI (SPY) Lab, advised by Florian Tramèr.

Visit my website for more information.

Pinned Loading

google-research/camel-prompt-injection google-research/camel-prompt-injection Public

Code for the paper "Defeating Prompt Injections by Design"

Jupyter Notebook 296 42
facebookresearch/prompt-siren facebookresearch/prompt-siren Public

A research workbench for developing and testing attacks against large language models, with a focus on prompt injection vulnerabilities and defenses.

Python 45 17
ethz-spylab/agentdojo ethz-spylab/agentdojo Public

A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.

Python 501 129
RobustBench/robustbench RobustBench/robustbench Public

RobustBench: a standardized adversarial robustness benchmark [NeurIPS 2021 Benchmarks and Datasets Track]

Python 772 102
JailbreakBench/jailbreakbench JailbreakBench/jailbreakbench Public

JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]

Python 557 66
ethz-spylab/satml-llm-ctf ethz-spylab/satml-llm-ctf Public

Code used to run the platform for the LLM CTF colocated with SaTML 2024

Python 28 7