This paper presents SimCLR: a simple framework for contrastive learning of visual representations. We simplify recently proposed contrastive self-supervised learning algorithms without requiring specialized architectures or a memory bank. In order to understand what enables the contrastive prediction tasks to learn useful representations, we systematically study the major components of our framework. We show that (1) composition of data augmentations plays a critical role in defining effective predictive tasks, (2) introducing a learnable nonlinear transformation between the representation and the contrastive loss substantially improves the quality of the learned representations, and (3) contrastive learning benefits from larger batch sizes and more training steps compared to supervised learning. By combining these findings, we are able to considerably outperform previous methods for self-supervised and semi-supervised learning on ImageNet. A linear classifier trained on self-supervised representations learned by SimCLR achieves 76.5% top-1 accuracy, which is a 7% relative improvement over previous state-of-the-art, matching the performance of a supervised ResNet-50. When fine-tuned on only 1% of the labels, we achieve 85.8% top-5 accuracy, outperforming AlexNet with 100X fewer labels.

A Simple Framework for Contrastive Learning of Visual Representations

Neural networks provide state-of-the-art results for most machine learning tasks. Unfortunately, neural networks are vulnerable to adversarial examples: given an input x and any target classification t, it is possible to find a new input x' that is similar to x but classified as t. This makes it difficult to apply neural networks in security-critical areas. Defensive distillation is a recently proposed approach that can take an arbitrary neural network, and increase its robustness, reducing the success rate of current attacks' ability to find adversarial examples from 95% to 0.5%.In this paper, we demonstrate that defensive distillation does not significantly increase the robustness of neural networks by introducing three new attack algorithms that are successful on both distilled and undistilled neural networks with 100% probability. Our attacks are tailored to three distance metrics used previously in the literature, and when compared to previous adversarial example generation algorithms, our attacks are often much more effective (and never worse). Furthermore, we propose using high-confidence adversarial examples in a simple transferability test we show can also be used to break defensive distillation. We hope our attacks will be used as a benchmark in future defense attempts to create neural networks that resist adversarial examples.

/pdf/towards-evaluating-the-robustness-of-neural-networks-40dfcinzm4.pdf

Towards Evaluating the Robustness of Neural Networks

Recent work has demonstrated that deep neural networks are vulnerable to adversarial examples---inputs that are almost indistinguishable from natural data and yet classified incorrectly by the network. In fact, some of the latest findings suggest that the existence of adversarial attacks may be an inherent weakness of deep learning models. To address this problem, we study the adversarial robustness of neural networks through the lens of robust optimization. This approach provides us with a broad and unifying view on much of the prior work on this topic. Its principled nature also enables us to identify methods for both training and attacking neural networks that are reliable and, in a certain sense, universal. In particular, they specify a concrete security guarantee that would protect against any adversary. These methods let us train networks with significantly improved resistance to a wide range of adversarial attacks. They also suggest the notion of security against a first-order adversary as a natural and broad security guarantee. We believe that robustness against such well-defined classes of adversaries is an important stepping stone towards fully resistant deep learning models. Code and pre-trained models are available at this https URL and this https URL.

Towards Deep Learning Models Resistant to Adversarial Attacks

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

Most existing machine learning classifiers are highly vulnerable to adversarial examples. An adversarial example is a sample of input data which has been modified very slightly in a way that is intended to cause a machine learning classifier to misclassify it. In many cases, these modifications can be so subtle that a human observer does not even notice the modification at all, yet the classifier still makes a mistake. Adversarial examples pose security concerns because they could be used to perform an attack on machine learning systems, even if the adversary has no access to the underlying model. Up to now, all previous work have assumed a threat model in which the adversary can feed data directly into the machine learning classifier. This is not always the case for systems operating in the physical world, for example those which are using signals from cameras and other sensors as an input. This paper shows that even in such physical world scenarios, machine learning systems are vulnerable to adversarial examples. We demonstrate this by feeding adversarial images obtained from cell-phone camera to an ImageNet Inception classifier and measuring the classification accuracy of the system. We find that a large fraction of adversarial examples are classified incorrectly even when perceived through the camera.

Adversarial examples in the physical world

Adversarial examples are malicious inputs crafted to induce misclassification. Commonly studied sensitivity-based adversarial examples introduce semantically-small changes to an input that result in a different model prediction. This paper studies a complementary failure mode, invariance-based adversarial examples, that introduce minimal semantic changes that modify an input's true label yet preserve the model's prediction. We demonstrate fundamental tradeoffs between these two types of adversarial examples. 
We show that defenses against sensitivity-based attacks actively harm a model's accuracy on invariance-based attacks, and that new approaches are needed to resist both attack types. In particular, we break state-of-the-art adversarially-trained and certifiably-robust models by generating small perturbations that the models are (provably) robust to, yet that change an input's class according to human labelers. Finally, we formally show that the existence of excessively invariant classifiers arises from the presence of overly-robust predictive features in standard datasets.

Fundamental Tradeoffs between Invariance and Sensitivity to Adversarial Perturbations

This paper describes a testing methodology for quantitatively assessing the risk that rare or unique training-data sequences are unintentionally memorized by generative sequence models---a common type of machine-learning model. Because such models are sometimes trained on sensitive data (e.g., the text of users' private messages), this methodology can benefit privacy by allowing deep-learning practitioners to select means of training that minimize such memorization. 
In experiments, we show that unintended memorization is a persistent, hard-to-avoid issue that can have serious consequences. Specifically, for models trained without consideration of memorization, we describe new, efficient procedures that can extract unique, secret sequences, such as credit card numbers. We show that our testing strategy is a practical and easy-to-use first line of defense, e.g., by describing its application to quantitatively limit data exposure in Google's Smart Compose, a commercial text-completion neural network trained on millions of users' email messages.

The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks

Model extraction allows an adversary to steal a copy of a remotely deployed machine learning model given access to its predictions. Adversaries are motivated to mount such attacks for a variety of reasons, ranging from reducing their computational costs, to eliminating the need to collect expensive training data, to obtaining a copy of a model in order to find adversarial examples, perform membership inference, or model inversion attacks. In this paper, we taxonomize the space of model extraction attacks around two objectives: accuracy, i.e., performing well on the underlying learning task, and fidelity, i.e., matching the predictions of the remote victim classifier on any input. To extract a high-accuracy model, we develop a learning-based attack which exploits the victim to supervise the training of an extracted model. Through analytical and empirical arguments, we then explain the inherent limitations that prevent any learningbased strategy from extracting a truly high-fidelity model—i.e., extracting a functionally-equivalent model whose predictions are identical to those of the victim model on all possible inputs. Addressing these limitations, we expand on prior work to develop the first practical functionally-equivalent extraction attack for direct extraction (i.e., without training) of a model’s weights. We perform experiments both on academic datasets and a state-of-the-art image classifier trained with 1 billion proprietary images. In addition to broadening the scope of model extraction research, our work demonstrates the practicality of model extraction attacks against production-grade systems.

High-Fidelity Extraction of Neural Network Models.

Adversarial examples are malicious inputs crafted to cause a model to misclassify them. Their most common instantiation, "perturbation-based" adversarial examples introduce changes to the input that leave its true label unchanged, yet result in a different model prediction. Conversely, "invariance-based" adversarial examples insert changes to the input that leave the model's prediction unaffected despite the underlying input's label having changed. 
In this paper, we demonstrate that robustness to perturbation-based adversarial examples is not only insufficient for general robustness, but worse, it can also increase vulnerability of the model to invariance-based adversarial examples. In addition to analytical constructions, we empirically study vision classifiers with state-of-the-art robustness to perturbation-based adversaries constrained by an $\ell_p$ norm. We mount attacks that exploit excessive model invariance in directions relevant to the task, which are able to find adversarial examples within the $\ell_p$ ball. In fact, we find that classifiers trained to be $\ell_p$-norm robust are more vulnerable to invariance-based adversarial examples than their undefended counterparts. 
Excessive invariance is not limited to models trained to be robust to perturbation-based $\ell_p$-norm adversaries. In fact, we argue that the term adversarial example is used to capture a series of model limitations, some of which may not have been discovered yet. Accordingly, we call for a set of precise definitions that taxonomize and address each of these shortcomings in learning.

/pdf/exploiting-excessive-invariance-caused-by-norm-bounded-4x56s8mgu8.pdf

Exploiting Excessive Invariance caused by Norm-Bounded Adversarial Robustness

No. I. ATTACKING “ATTACKS MEET INTERPRETABILITY” AmI (Attacks meet Interpretability) is an “attribute-steered” defense [3] to detect [1] adversarial examples [2] on facerecognition models. By applying interpretability techniques to a pre-trained neural network, AmI identifies “important” neurons. It then creates a second augmented neural network with the same parameters but increases the weight activations of important neurons. AmI rejects inputs where the original and augmented neural network disagree. We find that this defense (presented at at NeurIPS 2018 as a spotlight paper—the top 3% of submissions) is completely ineffective, and even defense-oblivious1 attacks reduce the detection rate to 0% on untargeted attacks. That is, AmI is no more robust to untargeted attacks than the undefended original network. Figure 1 shows selected adversarial examples that fool the AmI defense. We are incredibly grateful to the authors for releasing their source code2 which we build on3. We hope that future work will continue to release source code by publication time to accelerate progress in this field.

Nicholas Carlini

Papers

Fundamental Tradeoffs between Invariance and Sensitivity to Adversarial Perturbations

The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks

High-Fidelity Extraction of Neural Network Models.

Exploiting Excessive Invariance caused by Norm-Bounded Adversarial Robustness

Is AmI (Attacks Meet Interpretability) Robust to Adversarial Examples