-
Tight auditing of differentially private machine learning
M Nasr, J Hayes, T Steinke, B Balle, F Tramèr, M Jagielski, N Carlini, ...
32nd USENIX Security Symposium (USENIX Security 23), 1631-1648, 2023
-
Effectively using public data in privacy preserving Machine learning
M Nasr, S Mahloujifar, X Tang, P Mittal, A Houmansadr
-
Why Is Public Pretraining Necessary for Private Model Training?
A Ganesh, M Haghifam, M Nasr, S Oh, T Steinke, O Thakkar, AG Thakurta, ...
International Conference on Machine Learning, 10611-10627, 2023
-
Preventing generation of verbatim memorization in language models gives a false sense of privacy
D Ippolito, F Tramèr, M Nasr, C Zhang, M Jagielski, K Lee, ...
Proceedings of the 16th International Natural Language Generation Conference …, 2023
-
Extracting training data from diffusion models
N Carlini, J Hayes, M Nasr, M Jagielski, V Sehwag, F Tramer, B Balle, ...
32nd USENIX Security Symposium (USENIX Security 23), 5253-5270, 2023
-
Reverse-Engineering Decoding Strategies Given Blackbox Access to a Language Generation System
D Ippolito, N Carlini, K Lee, M Nasr, YW Yu
arXiv preprint arXiv:2309.04858, 2023
-
Universal and transferable adversarial attacks on aligned language models
A Zou, Z Wang, N Carlini, M Nasr, JZ Kolter, M Fredrikson
arXiv preprint arXiv:2307.15043, 2023
-
Universal and transferable adversarial attacks on aligned language models. arXiv 2023
A Zou, Z Wang, N Carlini, M Nasr, JZ Kolter, M Fredrikson
arXiv preprint arXiv:2307.15043, 2023
-
Academic Author How Names Order To
F Tramer, NCD Ippolito, C Zhang, M Jagielski, M Nasr, CACCK Lee
-
Synthetic Query Generation for Privacy-Preserving Deep Retrieval Systems using Differentially Private Language Models
AG Carranza, R Farahani, N Ponomareva, A Kurakin, M Jagielski, M Nasr
arXiv preprint arXiv:2305.05973, 2023
-
Privacy-Preserving Recommender Systems with Synthetic Query Generation using Differentially Private Large Language Models
AG Carranza, R Farahani, N Ponomareva, A Kurakin, M Jagielski, M Nasr
arXiv preprint arXiv:2305.05973, 2023
-
Report of the 1st Workshop on Generative AI and Law
AF Cooper, K Lee, J Grimmelmann, D Ippolito, C Callison-Burch, ...
arXiv preprint arXiv:2311.06477, 2023
-
Report of the 1st Workshop on Generative AI and Law
A Feder Cooper, K Lee, J Grimmelmann, D Ippolito, C Callison-Burch, ...
arXiv e-prints, arXiv: 2311.06477, 2023
-
Privacy Side Channels in Machine Learning Systems
E Debenedetti, G Severi, N Carlini, CA Choquette-Choo, M Jagielski, ...
arXiv preprint arXiv:2309.05610, 2023
-
Algorithms For Optimal Adaptation Of Diffusion Models To Reward Functions
KD Dvijotham, S Omidshafiei, K Lee, KM Collins, D Ramachandran, ...
ICML Workshop on New Frontiers in Learning, Control, and Dynamical Systems, 2023
-
Federated Ensemble Learning: Increasing the Capacity of Label Private Recommendation Systems
M Hejazinia, D Huba, I Leontiadis, K Maeng, M Malek, L Melis, I Mironov, ...