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

2019/02/20 by Gavin Weiguang Ding, Ding, Gavin Weiguang, Luyu Wang +3 · 7 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · #Advanced Malware Detection Techniques #Adversarial Robustness in Machine Learning #Bacillus and Francisella bacterial research #Computer Vision and Pattern Recognition (cs.CV) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · pdf · doi:10.48550/arxiv.1902.07623

openalex publication_date 2019/02/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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 .

Citations

• Intriguing properties of neural networks
• Adversarial Manipulation of Deep Representations
• Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
• A study of the effect of JPG compression on adversarial images
• Detecting Adversarial Samples from Artifacts
• Towards Deep Learning Models Resistant to Adversarial Attacks
• Countering Adversarial Images using Input Transformations
• On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models

Cited by

• Probabilistic Robustness for Free? Revisiting Training via a Benchmark
• Attribution of Gradient Based Adversarial Attacks for Reverse Engineering of Deceptions
• Constraining Logits by Bounded Function for Adversarial Robustness
• Voting based ensemble improves robustness of defensive models
• Adversarial Attack on Deep Product Quantization Network for Image Retrieval
• Amulet: a Python Library for Assessing Interactions Among ML Defenses and Risks
• Recurrent Attention Model with Log-Polar Mapping is Robust against Adversarial Attacks

Related

• AdvSecureNet: A Python Toolkit for Adversarial Machine Learning
• Adversarial Robustness Toolbox v1.0.0
• RobustBench: a standardized adversarial robustness benchmark
• Revisiting and Advancing Adversarial Training Through A Simple Baseline
• DeepRobust: A PyTorch Library for Adversarial Attacks and Defenses