83 citations · 221 across the 19 of their papers we have counts for
22 papers
Are you going to finish that? A Practical Study of the Partial Token Problem
Hao Xu, Alisa Liu, Jonathan Hayase +2
Language models (LMs) are trained over sequences of tokens, whereas users interact with LMs via text. This mismatch gives rise to the partial token problem, which occurs when a use…
Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model
Jacqueline He, Jonathan Hayase, Wen-tau Yih +3
Language models (LMs) tend to memorize portions of their training data and emit verbatim spans. When the underlying sources are sensitive or copyright-protected, such reproduction…
Broken Tokens? Your Language Model can Secretly Handle Non-Canonical Tokenizations
Brian Siyuan Zheng, Alisa Liu, Orevaoghene Ahia +3
Modern tokenizers employ deterministic algorithms to map text into a single "canonical" token sequence, yet the same string can be encoded as many non-canonical tokenizations using…
Sampling from Your Language Model One Byte at a Time
Jonathan Hayase, Alisa Liu, Noah A. Smith +1
Tokenization is used almost universally by modern language models, enabling efficient text representation using multi-byte or multi-character tokens. However, prior work has shown…
SuperBPE: Space Travel for Language Models
Alisa Liu, Jonathan Hayase, Valentin Hofmann +3
The assumption across nearly all language model (LM) tokenization schemes is that tokens should be subwords, i.e., contained within word boundaries. While providing a seemingly rea…
Scalable Fingerprinting of Large Language Models
Anshul Nasery, Jonathan Hayase, Creston Brooks +4
Model fingerprinting has emerged as a powerful tool for model owners to identify their shared model given API access. However, to lower false discovery rate, fight fingerprint leak…
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…
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…
Label Poisoning is All You Need
Rishi D. Jha, Jonathan Hayase, Sewoong Oh
In a backdoor attack, an adversary injects corrupted data into a model's training dataset in order to gain control over its predictions on images with a specific attacker-defined t…
DataComp: In search of the next generation of multimodal datasets
Samir Yitzhak Gadre, Gabriel Ilharco, Alex Fang +31
Multimodal datasets are a critical component in recent breakthroughs such as Stable Diffusion and GPT-4, yet their design does not receive the same research attention as model arch…
Zonotope Domains for Lagrangian Neural Network Verification
Matt Jordan, Jonathan Hayase, Alexandros G. Dimakis +1
Neural network verification aims to provide provable bounds for the output of a neural network for a given input range. Notable prior works in this domain have either generated bou…
Few-shot Backdoor Attacks via Neural Tangent Kernels
Jonathan Hayase, Sewoong Oh
In a backdoor attack, an attacker injects corrupted examples into the training set. The goal of the attacker is to cause the final trained model to predict the attacker's desired t…
Git Re-Basin: Merging Models modulo Permutation Symmetries
Samuel K. Ainsworth, Jonathan Hayase, Siddhartha Srinivasa
The success of deep learning is due in large part to our ability to solve certain massive non-convex optimization problems with relative ease. Though non-convex optimization is NP-…
Towards a Defense Against Federated Backdoor Attacks Under Continuous Training
Shuaiqi Wang, Jonathan Hayase, Giulia Fanti +1
Backdoor attacks are dangerous and difficult to prevent in federated learning (FL), where training data is sourced from untrusted clients over long periods of time. These difficult…
SPECTRE: Defending Against Backdoor Attacks Using Robust Statistics
Jonathan Hayase, Weihao Kong, Raghav Somani +1
Modern machine learning increasingly requires training on a large collection of data from multiple sources, not all of which can be trusted. A particularly concerning scenario is w…
The Futility of Bias-Free Learning and Search
George D. Montanez, Jonathan Hayase, Julius Lauw +3
Building on the view of machine learning as search, we demonstrate the necessity of bias in learning, quantifying the role of bias (measured relative to a collection of possible da…