238 citations · 805 across the 38 of their papers we have counts for
15 papers · 1 filter
Report of the 1st Workshop on Generative AI and Law
A. Feder Cooper, Katherine Lee, James Grimmelmann +32
This report presents the takeaways of the inaugural Workshop on Generative AI and Law (GenLaw), held in July 2023. A cross-disciplinary group of practitioners and scholars from com…
Scalable Extraction of Training Data from (Production) Language Models
Milad Nasr, Nicholas Carlini, Jonathan Hayase +7
This paper studies extractable memorization: training data that an adversary can efficiently extract by querying a machine learning model without prior knowledge of the training da…
Robust and Actively Secure Serverless Collaborative Learning
Olive Franzese, Adam Dziedzic, Christopher A. Choquette-Choo +7
Collaborative machine learning (ML) is widely used to enable institutions to learn better models from distributed data. While collaborative approaches to learning intuitively prote…
Privacy Amplification for Matrix Mechanisms
Christopher A. Choquette-Choo, Arun Ganesh, Thomas Steinke +1
Privacy amplification exploits randomness in data selection to provide tighter differential privacy (DP) guarantees. This analysis is key to DP-SGD's success in machine learning, b…
User Inference Attacks on Large Language Models
Nikhil Kandpal, Krishna Pillutla, Alina Oprea +3
Fine-tuning is a common and effective method for tailoring large language models (LLMs) to specialized tasks and applications. In this paper, we study the privacy implications of f…
Correlated Noise Provably Beats Independent Noise for Differentially Private Learning
Christopher A. Choquette-Choo, Krishnamurthy Dvijotham, Krishna Pillutla +3
Differentially private learning algorithms inject noise into the learning process. While the most common private learning algorithm, DP-SGD, adds independent Gaussian noise in each…
MADLAD-400: A Multilingual And Document-Level Large Audited Dataset
Sneha Kudugunta, Isaac Caswell, Biao Zhang +8
We introduce MADLAD-400, a manually audited, general domain 3T token monolingual dataset based on CommonCrawl, spanning 419 languages. We discuss the limitations revealed by self-a…
Privacy Side Channels in Machine Learning Systems
Edoardo Debenedetti, Giorgio Severi, Nicholas Carlini +5
Most current approaches for protecting privacy in machine learning (ML) assume that models exist in a vacuum. Yet, in reality, these models are part of larger systems that include…
Private Federated Learning with Autotuned Compression
Enayat Ullah, Christopher A. Choquette-Choo, Peter Kairouz +1
We propose new techniques for reducing communication in private federated learning without the need for setting or tuning compression rates. Our on-the-fly methods automatically ad…
Are aligned neural networks adversarially aligned?
Nicholas Carlini, Milad Nasr, Christopher A. Choquette-Choo +8
Large language models are now tuned to align with the goals of their creators, namely to be "helpful and harmless." These models should respond helpfully to user questions, but ref…
(Amplified) Banded Matrix Factorization: A unified approach to private training
Christopher A. Choquette-Choo, Arun Ganesh, Ryan McKenna +4
Matrix factorization (MF) mechanisms for differential privacy (DP) have substantially improved the state-of-the-art in privacy-utility-computation tradeoffs for ML applications in…
Federated Learning of Gboard Language Models with Differential Privacy
Zheng Xu, Yanxiang Zhang, Galen Andrew +5
We train language models (LMs) with federated learning (FL) and differential privacy (DP) in the Google Keyboard (Gboard). We apply the DP-Follow-the-Regularized-Leader (DP-FTRL)~\…
PaLM 2 Technical Report
Rohan Anil, Andrew M. Dai, Orhan Firat +125
We introduce PaLM 2, a new state-of-the-art language model that has better multilingual and reasoning capabilities and is more compute-efficient than its predecessor PaLM. PaLM 2 i…
Students Parrot Their Teachers: Membership Inference on Model Distillation
Matthew Jagielski, Milad Nasr, Christopher Choquette-Choo +2
Model distillation is frequently proposed as a technique to reduce the privacy leakage of machine learning. These empirical privacy defenses rely on the intuition that distilled ``…
Poisoning Web-Scale Training Datasets is Practical
Nicholas Carlini, Matthew Jagielski, Christopher A. Choquette-Choo +6
Deep learning models are often trained on distributed, web-scale datasets crawled from the internet. In this paper, we introduce two new dataset poisoning attacks that intentionall…