Follow
Edoardo Debenedetti
Edoardo Debenedetti
PhD student @ ETH Zürich
Verified email at inf.ethz.ch - Homepage
Title
Cited by
Cited by
Year
Robustbench: a standardized adversarial robustness benchmark
F Croce, M Andriushchenko, V Sehwag, E Debenedetti, N Flammarion, ...
Neural Information Processing Systems Track on Datasets and Benchmarks 1 (2021), 2021
6892021
A light recipe to train robust vision transformers
E Debenedetti, V Sehwag, P Mittal
2023 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), 225-253, 2023
542023
Jailbreakbench: An open robustness benchmark for jailbreaking large language models
P Chao, E Debenedetti, A Robey, M Andriushchenko, F Croce, V Sehwag, ...
arXiv preprint arXiv:2404.01318, 2024
392024
Privacy side channels in machine learning systems
E Debenedetti, G Severi, N Carlini, CA Choquette-Choo, M Jagielski, ...
33rd USENIX Security Symposium (USENIX Security 24), 6861-6848, 2024
212024
Evading black-box classifiers without breaking eggs
E Debenedetti, N Carlini, F Tramèr
2024 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), 408-424, 2024
62024
Scaling compute is not all you need for adversarial robustness
E Debenedetti, Z Wan, M Andriushchenko, V Sehwag, K Bhardwaj, ...
arXiv preprint arXiv:2312.13131, 2023
62023
AI Risk Management Should Incorporate Both Safety and Security
X Qi, Y Huang, Y Zeng, E Debenedetti, J Geiping, L He, K Huang, ...
arXiv preprint arXiv:2405.19524, 2024
42024
AgentDojo: A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents
E Debenedetti, J Zhang, M Balunović, L Beurer-Kellner, M Fischer, ...
arXiv preprint arXiv:2406.13352, 2024
22024
Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition
E Debenedetti, J Rando, D Paleka, SF Florin, D Albastroiu, N Cohen, ...
arXiv preprint arXiv:2406.07954, 2024
12024
Adversarial Search Engine Optimization for Large Language Models
F Nestaas, E Debenedetti, F Tramèr
arXiv preprint arXiv:2406.18382, 2024
2024
The system can't perform the operation now. Try again later.
Articles 1–10