The OOD results quoted in the papers use a range of classification network architectures.

Evaluating adversarial robustness amounts to finding the minimum perturbation needed to have an input sample misclassified. The inherent complexity of the underlying optimization requires current gradient-based attacks to be carefully tuned, initialized, and possibly executed for many computationally-demanding iterations, even if specialized to a given perturbation model.

Out-of-distribution (OOD) detection has recently gained substantial attention due to the importance of identifying out-of-domain samples in reliability and safety. Although OOD detection methods have advanced by a great deal, they are still susceptible to adversarial examples, which is a violation of their purpose. To mitigate this issue, several defenses have recently been proposed. Nevertheless, these efforts remained ineffective, as their evaluations are based on either small perturbation sizes, or weak attacks. In this work, we re-examine these defenses against an end-to-end PGD attack on in/out data with larger perturbation sizes, e.g. up to commonly used $\epsilon=8/255$ for the CIFAR-10 dataset.

Most machine learning models are vulnerable to adversarial examples, which poses security concerns on these models. Adversarial examples are crafted by applying subtle but intentionally worst-case modifications to examples from the dataset, leading the model to output a different answer from the original example. In this paper, adversarial examples are formed in an exactly opposite manner, which are significantly different from the original examples but result in the same answer. We propose a novel set of algorithms to produce such adversarial examples, including the negative iterative fast gradient sign method (NI-FGSM) and the negative iterative fast gradient method (NI-FGM), along with their momentum variants: the negative momentum iterative fast gradient sign method (NMI-FGSM) and the negative momentum iterative fast gradient method (NMI-FGM). Adversarial examples constructed by these methods could be used to perform an attack on machine learning systems in certain occasions. Moreover, our results show that the adversarial examples are not merely distributed in the neighbourhood of the examples from the dataset; instead, they are distributed extensively in the sample space.

For real-world applications, the DNN model as well as the training dataset, are often hidden from users. We conducted all experiments in an Nvidia-V100 GPU. Imagenet is licensed under Custom (noncommercial). For ResNet-50, DenseNet-121, VGG-16, Inception-v3, we adopt the pre-trained models provided by torchvision package. For SI and Admix, we adopt the parameters suggested in Wang et al.

As machine learning gets adopted into the industry quickly, trustworthiness is increasingly in focus. Yet, efficiency and sustainability of robust training pipelines still have to be established. In this work, we consider a simple pipeline for training adversarially robust decision trees and investigate the efficiency of each step. Our pipeline consists of three stages. Firstly, we choose the perturbation size automatically for each dataset. For that, we introduce a simple algorithm, instead of relying on intuition or prior work. Moreover, we show that the perturbation size can be estimated from smaller models than the one intended for full training, and thus significant gains in efficiency can be achieved. Secondly, we train state-of-the-art adversarial training methods and evaluate them regarding both their training time and adversarial accuracy. Thirdly, we certify the robustness of each of the models thus obtained and investigate the time required for this. We find that verification time, which is critical to the efficiency of the full pipeline, is not correlated with training time.