advertorch v0.1: An Adversarial Robustness Toolbox based on PyTorch

advertorch is a toolbox for adversarial robustness research. It contains various implementations for attacks, defenses and robust training methods. advertorch is built on PyTorch (Paszke et al., 2017), and leverages the advantages of the dynamic computational graph to provide concise and efficient reference implementations. The code is licensed under the LGPL license and is open sourced at https://github.com/BorealisAI/advertorch .

Security & robustness cs.LG cs.CR cs.CV stat.ML Adversarial Robustness in Machine Learning Bacillus and Francisella bacterial research Advanced Malware Detection Techniques Computer Science Mathematics

Paper

References (35)

01MMA Training: Direct Input Space Margin Maximization through Adversarial TrainingG. Ding, Yash Sharma, Kry Yik-Chau Lui et al.2018 · International Conference on Learning Representations · 312 citations In Library

02On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust ModelsSven Gowal, K. Dvijotham, Robert Stanforth et al.2018 · arXiv.org · 645 citations In Library

03On the Sensitivity of Adversarial Robustness to Input Data DistributionsG. Ding, Kry Yik-Chau Lui, Xiaomeng Jin et al.2018 · International Conference on Learning Representations · 67 citations In Library

04Are adversarial examples inevitable?Ali Shafahi, W. R. Huang, Christoph Studer et al.2018 · International Conference on Learning Representations · 305 citations In Library

05Differentiable Abstract Interpretation for Provably Robust Neural NetworksM. Mirman, T. Gehr, Martin T. Vechev2018 · International Conference on Machine Learning · 584 citations

06Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial ExamplesAnish Athalye, Nicholas Carlini, D. Wagner2018 · International Conference on Machine Learning · 3.6k citations In Library

07Evaluating the Robustness of Neural Networks: An Extreme Value Theory ApproachTsui-Wei Weng, Huan Zhang, Pin-Yu Chen et al.2018 · International Conference on Learning Representations · 524 citations In Library

08Spatially Transformed Adversarial ExamplesChaowei Xiao, Jun-Yan Zhu, Bo Li et al.2018 · International Conference on Learning Representations · 573 citations In Library

09Characterizing Adversarial Subspaces Using Local Intrinsic DimensionalityXingjun Ma, Bo Li, Yisen Wang et al.2018 · International Conference on Learning Representations · 854 citations In Library

10Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning ModelsWieland Brendel, Jonas Rauber, M. Bethge2017 · International Conference on Learning Representations · 1.6k citations In Library

11Provable defenses against adversarial examples via the convex outer adversarial polytopeJ. Kolter, Eric Wong2017 · International Conference on Machine Learning · 1.6k citations In Library

12Automatic differentiation in PyTorchAdam Paszke, Sam Gross, Soumith Chintala et al.2017 · 16k citations

Scroll for more · 23 remaining

Similar papers

DeepRobust: A PyTorch Library for Adversarial Attacks and DefensesYaxin Li, Wei Jin, Han Xu et al.2020 · arXiv (Cornell University) · 166 citations In Library

Torchattacks: A PyTorch Repository for Adversarial AttacksHoki Kim2020 · arXiv (Cornell University) · 276 citations In Library

Adversarial Robustness Toolbox v0.2.2Maria-Irina Nicolae, M. Sinn, T. Minh et al.2018 · arXiv.org · 57 citations In Library

DeepRobust: a Platform for Adversarial Attacks and DefensesYaxin Li, Wei Jin, Han Xu et al.2021 · Proceedings of the AAAI Conference on Artificial Intelligence · 43 citations In Library

Adversarial Robustness Toolbox v1.0.0Maria-Irina Nicolae, M. Sinn, Minh-Ngoc Tran et al.2018 · arXiv: Learning · 562 citations In Library

AdvSecureNet: A Python Toolkit for Adversarial Machine LearningMelih Catal, Manuel Günther2024 · arXiv (Cornell University) · 0 citations In Library

RobArch: Designing Robust Architectures against Adversarial AttacksShengyun Peng, Weilin Xu, Cory Cornelius et al.2023 · arXiv (Cornell University) · 8 citations In Library

RobustBench: a standardized adversarial robustness benchmarkFrancesco Croce, Maksym Andriushchenko, Vikash Sehwag et al.2020 · arXiv (Cornell University) · 928 citations In Library

Adversarial Robustness in Deep Learning: From Practices to TheoriesHan Xu, Yaxin Li, Xiaorui Liu et al.2021 · Knowledge Discovery and Data Mining · 1 citation In Library

Adversarial Training and Robustness in Machine Learning FrameworksMrs. Sangeetha G, Mr. Bharath K, Mr. Balamanikandan S et al.2024 · International Journal of Advanced Research in Science Communication and Technology In Library

Source of record

arXiv

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal