273 citations · 1.4k across the 27 of their papers we have counts for
5 papers · 1 filter
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…
SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore
Sewon Min, Suchin Gururangan, Eric Wallace +4
The legality of training language models (LMs) on copyrighted or otherwise restricted data is under intense debate. However, as we show, model performance significantly degrades if…
The False Promise of Imitating Proprietary LLMs
Arnav Gudibande, Eric Wallace, Charlie Snell +5
An emerging method to cheaply improve a weaker language model is to finetune it on outputs from a stronger model, such as a proprietary system like ChatGPT (e.g., Alpaca, Self-Inst…
Poisoning Language Models During Instruction Tuning
Alexander Wan, Eric Wallace, Sheng Shen +1
Instruction-tuned LMs such as ChatGPT, FLAN, and InstructGPT are finetuned on datasets that contain user-submitted examples, e.g., FLAN aggregates numerous open-source datasets and…
Extracting Training Data from Diffusion Models
Nicholas Carlini, Jamie Hayes, Milad Nasr +6
Image diffusion models such as DALL-E 2, Imagen, and Stable Diffusion have attracted significant attention due to their ability to generate high-quality synthetic images. In this w…