activity
20162020
most citedOn Evaluating Adversarial Robustness

579 citations · 1.2k across the 8 of their papers we have counts for

collaborators

14 papers

stat.ML202026 cited

Tempered Sigmoid Activations for Deep Learning with Differential Privacy

Nicolas Papernot, Abhradeep Thakurta, Shuang Song +2

Because learning sometimes involves sensitive data, machine learning algorithms have been extended to offer privacy for training data. In practice, this has been mostly an aftertho…

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…

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…

stat.ML20192 cited

Improving Differentially Private Models with Active Learning

Zhengli Zhao, Nicolas Papernot, Sameer Singh +2

Broad adoption of machine learning techniques has increased privacy concerns for models trained on sensitive data such as medical records. Existing techniques for training differen…

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…

cs.LG2019

MixMatch: A Holistic Approach to Semi-Supervised Learning

David Berthelot, Nicholas Carlini, Ian Goodfellow +3

Semi-supervised learning has proven to be a powerful paradigm for leveraging unlabeled data to mitigate the reliance on large labeled datasets. In this work, we unify the current d…