83 citations · 221 across the 19 of their papers we have counts for
7 papers · 1 filter
OML: A Primitive for Reconciling Open Access with Owner Control in AI Model Distribution
Zerui Cheng, Edoardo Contente, Ben Finch +9
The current paradigm of AI model distribution presents a fundamental dichotomy: models are either closed and API-gated, sacrificing transparency and local execution, or openly dist…
Monge-Kantorovich Fitting With Sobolev Budgets
Forest Kobayashi, Jonathan Hayase, Young-Heon Kim
Given , we consider the problem of ``best'' approximating an probability measure via an measure such that has bounded to…
Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data?
Jonathan Hayase, Alisa Liu, Yejin Choi +2
The pretraining data of today's strongest language models is opaque; in particular, little is known about the proportions of various domains or languages represented. In this work,…
PLeaS -- Merging Models with Permutations and Least Squares
Anshul Nasery, Jonathan Hayase, Pang Wei Koh +1
The democratization of machine learning systems has made the process of fine-tuning accessible to practitioners, leading to a wide range of open-source models fine-tuned on special…
Insufficient Statistics Perturbation: Stable Estimators for Private Least Squares
Gavin Brown, Jonathan Hayase, Samuel Hopkins +5
We present a sample- and time-efficient differentially private algorithm for ordinary least squares, with error that depends linearly on the dimension and is independent of the con…
Stealing Part of a Production Language Model
Nicholas Carlini, Daniel Paleka, Krishnamurthy Dj Dvijotham +11
We introduce the first model-stealing attack that extracts precise, nontrivial information from black-box production language models like OpenAI's ChatGPT or Google's PaLM-2. Speci…
Query-Based Adversarial Prompt Generation
Jonathan Hayase, Ema Borevkovic, Nicholas Carlini +2
Recent work has shown it is possible to construct adversarial examples that cause an aligned language model to emit harmful strings or perform harmful behavior. Existing attacks wo…