activity
20172020
most citedOn Evaluating Adversarial Robustness

579 citations · 1k across the 5 of their papers we have counts for

collaborators

12 papers

cs.LG2020

Cryptanalytic Extraction of Neural Network Models

Nicholas Carlini, Matthew Jagielski, Ilya Mironov

We argue that the machine learning problem of model extraction is actually a cryptanalytic problem in disguise, and should be studied as such. Given oracle access to a neural netwo…

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

FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence

Kihyuk Sohn, David Berthelot, Chun-Liang Li +6

Semi-supervised learning (SSL) provides an effective means of leveraging unlabeled data to improve a model's performance. In this paper, we demonstrate the power of a simple combin…

cs.LG2019164 cited

ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring

David Berthelot, Nicholas Carlini, Ekin D. Cubuk +4

We improve the recently-proposed "MixMatch" semi-supervised learning algorithm by introducing two new techniques: distribution alignment and augmentation anchoring. Distribution al…

cs.LG201919 cited

Distribution Density, Tails, and Outliers in Machine Learning: Metrics and Applications

Nicholas Carlini, Úlfar Erlingsson, Nicolas Papernot

We develop techniques to quantify the degree to which a given (training or testing) example is an outlier in the underlying distribution. We evaluate five methods to score examples…

cs.LG2019

High Accuracy and High Fidelity Extraction of Neural Networks

Matthew Jagielski, Nicholas Carlini, David Berthelot +2

In a model extraction attack, an adversary steals a copy of a remotely deployed machine learning model, given oracle prediction access. We taxonomize model extraction attacks aroun…