Understanding Misclassifications by Attributes

In this paper, we aim to understand and explain the decisions of deep neural networks by studying the behavior of predicted attributes when adversarial examples are introduced. We study the changes in attributes for clean as well as adversarial images in both standard and adversarially robust networks. We propose a metric to quantify the robustness of an adversarially robust network against adversarial attacks. In a standard network, attributes predicted for adversarial images are consistent with the wrong class, while attributes predicted for the clean images are consistent with the true class. In an adversarially robust network, the attributes predicted for adversarial images classified correctly are consistent with the true class. Finally, we show that the ability to robustify a network varies for different datasets. For the fine grained dataset, it is higher as compared to the coarse-grained dataset. Additionally, the ability to robustify a network increases with the increase in adversarial noise.

Interpreting Adversarial Examples with Attributes

Deep computer vision systems being vulnerable to imperceptible and carefully crafted noise have raised questions regarding the robustness of their decisions. We take a step back and approach this problem from an orthogonal direction. We propose to enable black-box neural networks to justify their reasoning both for clean and for adversarial examples by leveraging attributes, i.e. visually discriminative properties of objects. We rank attributes based on their class relevance, i.e. how the classification decision changes when the input is visually slightly perturbed, as well as image relevance, i.e. how well the attributes can be localized on both clean and perturbed images. We present comprehensive experiments for attribute prediction, adversarial example generation, adversarially robust learning, and their qualitative and quantitative analysis using predicted attributes on three benchmark datasets.

Defending against Universal Perturbations with Shared Adversarial Training

Classifiers such as deep neural networks have been shown to be vulnerable against adversarial perturbations on problems with high-dimensional input space. While adversarial training improves the robustness of image classifiers against such adversarial perturbations, it leaves them sensitive to perturbations on a non-negligible fraction of the inputs. In this work, we show that adversarial training is more effective in preventing universal perturbations, where the same perturbation needs to fool a classifier on many inputs. Moreover, we investigate the trade-off between robustness against universal perturbations and performance on unperturbed data and propose an extension of adversarial training that handles this trade-off more gracefully. We present results for image classification and semantic segmentation to showcase that universal perturbations that fool a model hardened with adversarial training become clearly perceptible and show patterns of the target scene.

Neural Architecture Search: A Survey

Deep Learning has enabled remarkable progress over the last years on a variety of tasks, such as image recognition, speech recognition, and machine translation. One crucial aspect for this progress are novel neural architectures. Currently employed architectures have mostly been developed manually by human experts, which is a time-consuming and error-prone process. Because of this, there is growing interest in automated neural architecture search methods. We provide an overview of existing work in this field of research and categorize them according to three dimensions: search space, search strategy, and performance estimation strategy.

Efficient Multi-objective Neural Architecture Search via Lamarckian Evolution

Architecture search aims at automatically finding neural architectures that are competitive with architectures designed by human experts. While recent approaches have achieved state-of-the-art predictive performance for image recognition, they are problematic under resource constraints for two reasons: (1) the neural architectures found are solely optimized for high predictive performance, without penalizing excessive resource consumption; (2) most architecture search methods require vast computational resources. We address the first shortcoming by proposing LEMONADE, an evolutionary algorithm for multi-objective architecture search that allows approximating the Pareto-front of architectures under multiple objectives, such as predictive performance and number of parameters, in a single run of the method. We address the second shortcoming by proposing a Lamarckian inheritance mechanism for LEMONADE which generates children networks that are warmstarted with the predictive performance of their trained parents. This is accomplished by using (approximate) network morphism operators for generating children. The combination of these two contributions allows finding models that are on par or even outperform different-sized NASNets, MobileNets, MobileNets V2 and Wide Residual Networks on CIFAR-10 and ImageNet64x64 within only one week on eight GPUs, which is about 20-40x less compute power than previous architecture search methods that yield state-of-the-art performance.

Scaling provable adversarial defenses

Recent work has developed methods for learning deep network classifiers that are provably robust to norm-bounded adversarial perturbation; however, these methods are currently only possible for relatively small feedforward networks. In this paper, in an effort to scale these approaches to substantially larger models, we extend previous work in three main directions. First, we present a technique for extending these training procedures to much more general networks, with skip connections (such as ResNets) and general nonlinearities; the approach is fully modular, and can be implemented automatically (analogous to automatic differentiation). Second, in the specific case of $\ell_\infty$ adversarial perturbations and networks with ReLU nonlinearities, we adopt a nonlinear random projection for training, which scales linearly in the number of hidden units (previous approaches scaled quadratically). Third, we show how to further improve robust error through cascade models. On both MNIST and CIFAR data sets, we train classifiers that improve substantially on the state of the art in provable robust adversarial error bounds: from 5.8% to 3.1% on MNIST (with $\ell_\infty$ perturbations of $\epsilon=0.1$), and from 80% to 36.4% on CIFAR (with $\ell_\infty$ perturbations of $\epsilon=2/255$). Code for all experiments in the paper is available at https://github.com/locuslab/convex_adversarial/.

Universal Adversarial Perturbations Against Semantic Image Segmentation

While deep learning is remarkably successful on perceptual tasks, it was also shown to be vulnerable to adversarial perturbations of the input. These perturbations denote noise added to the input that was generated specifically to fool the system while being quasi-imperceptible for humans. More severely, there even exist universal perturbations that are input-agnostic but fool the network on the majority of inputs. While recent work has focused on image classification, this work proposes attacks against semantic image segmentation: we present an approach for generating (universal) adversarial perturbations that make the network yield a desired target segmentation as output. We show empirically that there exist barely perceptible universal noise patterns which result in nearly the same predicted segmentation for arbitrary inputs. Furthermore, we also show the existence of universal noise which removes a target class (e.g., all pedestrians) from the segmentation while leaving the segmentation mostly unchanged otherwise.

Adversarial Examples for Semantic Image Segmentation

Machine learning methods in general and Deep Neural Networks in particular have shown to be vulnerable to adversarial perturbations. So far this phenomenon has mainly been studied in the context of whole-image classification. In this contribution, we analyse how adversarial perturbations can affect the task of semantic segmentation. We show how existing adversarial attackers can be transferred to this task and that it is possible to create imperceptible adversarial perturbations that lead a deep network to misclassify almost all pixels of a chosen class while leaving network prediction nearly unchanged outside this class.

On Detecting Adversarial Perturbations

Machine learning and deep learning in particular has advanced tremendously on perceptual tasks in recent years. However, it remains vulnerable against adversarial perturbations of the input that have been crafted specifically to fool the system while being quasi-imperceptible to a human. In this work, we propose to augment deep neural networks with a small "detector" subnetwork which is trained on the binary classification task of distinguishing genuine data from data containing adversarial perturbations. Our method is orthogonal to prior work on addressing adversarial perturbations, which has mostly focused on making the classification network itself more robust. We show empirically that adversarial perturbations can be detected surprisingly well even though they are quasi-imperceptible to humans. Moreover, while the detectors have been trained to detect only a specific adversary, they generalize to similar and weaker adversaries. In addition, we propose an adversarial attack that fools both the classifier and the detector and a novel training procedure for the detector that counteracts this attack.

Minimum Regret Search for Single- and Multi-Task Optimization

We propose minimum regret search (MRS), a novel acquisition function for Bayesian optimization. MRS bears similarities with information-theoretic approaches such as entropy search (ES). However, while ES aims in each query at maximizing the information gain with respect to the global maximum, MRS aims at minimizing the expected simple regret of its ultimate recommendation for the optimum. While empirically ES and MRS perform similar in most of the cases, MRS produces fewer outliers with high simple regret than ES. We provide empirical results both for a synthetic single-task optimization problem as well as for a simulated multi-task robotic control problem.