activity
20172026
most citedThe Space of Transferable Adversarial Examples

438 citations · 670 across the 13 of their papers we have counts for

collaborators
Showing cs.CRShow all

10 papers · 1 filter

cs.CR2026

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…

cs.CR2024

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…

cs.CR2024

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…

cs.CR2021

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…

cs.CR2020

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…

cs.CR2020

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…