activity
20172026
most citedThe Space of Transferable Adversarial Examples

438 citations · 670 across the 14 of their papers we have counts for

collaborators
Showing 2020Show all

5 papers · 1 filter

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.LG202065 cited

Differentially Private Learning Needs Better Features (or Much More Data)

Florian Tramèr, Dan Boneh

We demonstrate that differentially private machine learning has not yet reached its "AlexNet moment" on many canonical vision tasks: linear models trained on handcrafted features s…

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…

cs.LG2020

On Adaptive Attacks to Adversarial Example Defenses

Florian Tramer, Nicholas Carlini, Wieland Brendel +1

Adaptive attacks have (rightfully) become the de facto standard for evaluating defenses to adversarial examples. We find, however, that typical adaptive evaluations are incomplete.…

cs.LG2020

Fundamental Tradeoffs between Invariance and Sensitivity to Adversarial Perturbations

Florian Tramèr, Jens Behrmann, Nicholas Carlini +2

Adversarial examples are malicious inputs crafted to induce misclassification. Commonly studied sensitivity-based adversarial examples introduce semantically-small changes to an in…