• Grad-CAM

  • Referenced in 21 articles [sw35098]
  • into their failure modes, (b) are robust to adversarial images, (c) outperform previous methods...
  • mixup

  • Referenced in 11 articles [sw35857]
  • behaviors such as memorization and sensitivity to adversarial examples. In this work, we propose mixup ... memorization of corrupt labels, increases the robustness to adversarial examples, and stabilizes the training...
  • DeepFool

  • Referenced in 14 articles [sw20937]
  • deep networks, and thus reliably quantify the robustness of these classifiers. Extensive experimental results show ... task of computing adversarial perturbations and making classifiers more robust. DeepFool: a simple and accurate...
  • MixTrain

  • Referenced in 1 article [sw31370]
  • attacks. The most promising defenses, adversarially robust training and verifiably robust training, have limitations that ... restrict their practical applications. The adversarially robust training only makes the networks robust against ... more computational and memory overhead than adversarially robust training. We propose two novel techniques, stochastic ... verifiably robust training and adversarially robust training schemes, respectively. Furthermore, MixTrain easily scales to larger...
  • SecML Malware

  • Referenced in 1 article [sw38335]
  • secml-malware: A Python Library for Adversarial Robustness Evaluation of Windows Malware Classifiers. Machine learning ... detectors can be evaded by well-crafted, adversarial manipulations of input malware, highlighting the need ... that can ease and automate the adversarial robustness evaluation of such detectors. To this ... used to assess the adversarial robustness of Windows malware detectors, and it can be easily...
  • ART

  • Referenced in 2 articles [sw37566]
  • Adversarial Robustness Toolbox (ART) is a Python library for Machine Learning Security. ART provides tools ... Machine Learning models and applications against the adversarial threats of Evasion, Poisoning, Extraction, and Inference...
  • advertorch

  • Referenced in 1 article [sw32885]
  • advertorch v0.1: An Adversarial Robustness Toolbox based on PyTorch. advertorch is a toolbox for adversarial...
  • CLAIMED

  • Referenced in 1 article [sw37562]
  • more popular but constraints on explainability, adversarial robustness and fairness are often major concerns ... Fairness360 toolkit and the Adversarial Robustness Toolkit on top of ElyraAI, Kubeflow, Kubernetes and JupyterLab...
  • Foolbox

  • Referenced in 3 articles [sw20935]
  • v0.8.0: A Python toolbox to benchmark the robustness of machine learning models. Even todays most ... generate such adversarial perturbations and to quantify and compare the robustness of machine learning models ... most comparable robustness measure is the minimum perturbation needed to craft an adversarial example...
  • BERTScore

  • Referenced in 5 articles [sw33891]
  • adversarial paraphrase detection task to show that BERTScore is more robust to challenging examples when...
  • BRMaximin

  • Referenced in 4 articles [sw38759]
  • leveraging robust optimization, stochastic programming, and distributionally robust optimization techniques, our set of models yields ... normal form game with incomplete knowledge regarding adversary rationality. A software package implementing these constructs ... applied to illustrative instances, demonstrating how behaviorally robust strategies vary in accordance with the underlying...
  • TextFlint

  • Referenced in 1 article [sw37742]
  • this work, we propose a multilingual robustness evaluation platform for NLP tasks (TextFlint) that incorporates ... specific transformation, adversarial attack, subpopulation, and their combinations to provide comprehensive robustness analysis. TextFlint enables...
  • NATTACK

  • Referenced in 1 article [sw32886]
  • Networks. Powerful adversarial attack methods are vital for understanding how to construct robust deep neural ... this paper, we propose a black-box adversarial attack algorithm that can defeat both vanilla...
  • OpenAttack

  • Referenced in 1 article [sw37746]
  • paper, we present an open-source textual adversarial attack toolkit named OpenAttack. It currently builds ... measuring robustness of a victim model, assisting in developing new attack models, and adversarial training...
  • DEEPSEC

  • Referenced in 1 article [sw41286]
  • arms race between adversaries and defenders. Such plethora of emerging attacks and defenses raise many ... robust than individuals? Yet, due to the lack of platforms for comprehensive evaluation on adversarial...
  • GANSim

  • Referenced in 4 articles [sw40967]
  • subsurface resources. Recently, researchers have used generative adversarial networks (GANs) for conditional facies modeling, where ... quantitative assessment. The trained generators are quite robust in generating high-quality facies models conditioned...
  • Advbox

  • Referenced in 1 article [sw41290]
  • emph{Advbox} is a toolbox to generate adversarial examples that fool neural networks in PaddlePaddle ... Keras, TensorFlow and it can benchmark the robustness of machine learning models. Compared to previous...
  • DLFuzz

  • Referenced in 2 articles [sw41845]
  • significant importance to ensure the reliability and robustness of DL systems. Existing testing methodologies always ... referencing check, but could generate 338.59% more adversarial inputs with 89.82% smaller perturbations, averagely obtain...
  • MRCpy

  • Referenced in 1 article [sw39713]
  • risk classifiers (MRCs) that are based on robust risk minimization and can utilize ... regularized logistic regression, zero-one adversarial, and maximum entropy machines. In addition, MRCpy implements recent...
  • CovidGAN

  • Referenced in 1 article [sw41862]
  • images by developing an Auxiliary Classifier Generative Adversarial Network (ACGAN) based model called CovidGAN ... COVID-19 detection and lead to more robust systems of radiology...