2.3k citations · 5.1k across the 13 of their papers we have counts for
14 papers
AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptation
David Berthelot, Rebecca Roelofs, Kihyuk Sohn +2
We extend semi-supervised learning to the problem of domain adaptation to learn significantly higher-accuracy models that train on one data distribution and test on a different one…
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…
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…
Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition
Yao Qin, Nicholas Carlini, Ian Goodfellow +2
Adversarial examples are inputs to machine learning models designed by an adversary to cause an incorrect output. So far, adversarial examples have been studied most extensively in…
On Evaluating Adversarial Robustness
Nicholas Carlini, Anish Athalye, Nicolas Papernot +6
Correctly evaluating defenses against adversarial examples has proven to be extremely difficult. Despite the significant amount of recent work attempting to design defenses that wi…
On the Robustness of the CVPR 2018 White-Box Adversarial Example Defenses
Anish Athalye, Nicholas Carlini
Neural networks are known to be vulnerable to adversarial examples. In this note, we evaluate the two white-box defenses that appeared at CVPR 2018 and find they are ineffective: w…
The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks
Nicholas Carlini, Chang Liu, Úlfar Erlingsson +2
This paper describes a testing methodology for quantitatively assessing the risk that rare or unique training-data sequences are unintentionally memorized by generative sequence mo…
Adversarial Example Defenses: Ensembles of Weak Defenses are not Strong
Warren He, James Wei, Xinyun Chen +2
Ongoing research has proposed several methods to defend neural networks against adversarial examples, many of which researchers have shown to be ineffective. We ask whether a stron…
Technical Report on the CleverHans v2.1.0 Adversarial Examples Library
Nicolas Papernot, Fartash Faghri, Nicholas Carlini +23
CleverHans is a software library that provides standardized reference implementations of adversarial example construction techniques and adversarial training. The library may be us…