Torchattacks: A PyTorch Repository for Adversarial Attacks
arXiv:2010.01950
Abstract
Torchattacks is a PyTorch library that contains adversarial attacks to generate adversarial examples and to verify the robustness of deep learning models. The code can be found at https://github.com/Harry24k/adversarial-attacks-pytorch.
arXiv comment6 pages
References in corpus (6)
- Adam: A Method for Stochastic Optimization
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Theoretically Principled Trade-off between Robustness and Accuracy
- Fast is better than free: Revisiting adversarial training
- Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network
- Comment on "Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network"
Cited by in corpus (14)
- FedDef: Defense Against Gradient Leakage in Federated Learning-based Network Intrusion Detection Systems
- Pixle: a fast and effective black-box attack based on rearranging pixels
- Towards Robust Stability Prediction in Smart Grids: GAN-based Approach under Data Constraints and Adversarial Challenges
- Adversarial Visual Robustness by Causal Intervention
- DiffDefense: Defending against Adversarial Attacks via Diffusion Models
- k-Mixup Regularization for Deep Learning via Optimal Transport
- Multi-objective Search of Robust Neural Architectures against Multiple Types of Adversarial Attacks
- Benchmarking the Accuracy and Robustness of Feedback Alignment Algorithms
- Towards Black-box Attacks on Deep Learning Apps
- Soft Adversarial Training Can Retain Natural Accuracy
- Resilience from Diversity: Population-based approach to harden models against adversarial attacks
- Multi-Expert Adversarial Attack Detection in Person Re-identification Using Context Inconsistency
- Bridged Adversarial Training
- Sparse Coding Frontend for Robust Neural Networks