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