438 citations · 670 across the 13 of their papers we have counts for
10 papers · 1 filter
Large-scale online deanonymization with LLMs
Simon Lermen, Daniel Paleka, Joshua Swanson +3
We show that large language models can be used to perform at-scale deanonymization. With full Internet access, our agent can re-identify Hacker News users and Anthropic Interviewer…
SoK: Watermarking for AI-Generated Content
Xuandong Zhao, Sam Gunn, Miranda Christ +11
As the outputs of generative AI (GenAI) techniques improve in quality, it becomes increasingly challenging to distinguish them from human-created content. Watermarking schemes are…
Persistent Pre-Training Poisoning of LLMs
Yiming Zhang, Javier Rando, Ivan Evtimov +5
Large language models are pre-trained on uncurated text datasets consisting of trillions of tokens scraped from the Web. Prior work has shown that: (1) web-scraped pre-training dat…
NeuraCrypt is not private
Nicholas Carlini, Sanjam Garg, Somesh Jha +3
NeuraCrypt (Yara et al. arXiv 2021) is an algorithm that converts a sensitive dataset to an encoded dataset so that (1) it is still possible to train machine learning models on the…
Extracting Training Data from Large Language Models
Nicholas Carlini, Florian Tramer, Eric Wallace +9
It has become common to publish large (billion parameter) language models that have been trained on private datasets. This paper demonstrates that in such settings, an adversary ca…
Is Private Learning Possible with Instance Encoding?
Nicholas Carlini, Samuel Deng, Sanjam Garg +6
A private machine learning algorithm hides as much as possible about its training data while still preserving accuracy. In this work, we study whether a non-private learning algori…