khalooei / LSALinks
LSA : Layer Sustainability Analysis framework for the analysis of layer vulnerability in a given neural network. LSA can be a helpful toolkit to assess deep neural networks and to extend the adversarial training approaches towards improving the sustainability of model layers via layer monitoring and analysis.
☆18Updated 3 years ago
Alternatives and similar repositories for LSA
Users that are interested in LSA are comparing it to the libraries listed below
Sorting:
- Adversarial Robustness, White-box, Adversarial Attack☆52Updated 3 years ago
- Code for Prior-Guided Adversarial Initialization for Fast Adversarial Training (ECCV2022)☆28Updated 3 years ago
- Code for LAS-AT: Adversarial Training with Learnable Attack Strategy (CVPR2022)☆118Updated 3 years ago
- ☆53Updated 4 years ago
- Pytorch Implementation of APE-GAN☆15Updated 8 years ago
- [ICLR 2022] Reliable Adversarial Distillation with Unreliable Teachers☆22Updated 3 years ago
- ☆31Updated last year
- This is the official code for "Revisiting Adversarial Robustness Distillation: Robust Soft Labels Make Student Better"☆45Updated 4 years ago
- Membership Inference Attacks and Defenses in Neural Network Pruning☆28Updated 3 years ago
- Implementation of adversarial training under fast-gradient sign method (FGSM), projected gradient descent (PGD) and CW using Wide-ResNet-…☆40Updated 5 years ago
- Learnable Boundary Guided Adversarial Training (ICCV2021)☆38Updated last year
- Code for "Improving Robustness of Vision Transformers by Reducing Sensitivity to Patch Corruptions"☆14Updated 2 years ago
- Removing Adversarial Noise in Class Activation Feature Space☆14Updated 2 years ago
- ☆63Updated 4 years ago
- ☆12Updated 11 months ago
- Example of the attack described in the paper "Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization"☆21Updated 6 years ago
- Towards Efficient and Effective Adversarial Training, NeurIPS 2021☆17Updated 3 years ago
- Codes for ICCV 2021 paper "AGKD-BML: Defense Against Adversarial Attack by Attention Guided Knowledge Distillation and Bi-directional Met…☆12Updated 3 years ago
- [USENIX Security 2022] Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecture☆17Updated 3 years ago
- ☆29Updated 5 years ago
- ☆58Updated 3 years ago
- [NeurIPS 2021] "Class-Disentanglement and Applications in Adversarial Detection and Defense"☆46Updated 4 years ago
- Universal Adversarial Perturbations (UAPs) for PyTorch☆49Updated 4 years ago
- The Code of ECCV2022:Enhanced Accuracy and Robustness via Multi-Teacher Adversarial Distillation☆36Updated 3 months ago
- Foolbox implementation for NeurIPS 2021 Paper: "Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints".☆24Updated 3 years ago
- ☆61Updated 2 years ago
- Code for the paper "Better Diffusion Models Further Improve Adversarial Training" (ICML 2023)☆146Updated 2 years ago
- Code for Backdoor Attacks Against Dataset Distillation☆35Updated 2 years ago
- Code for Boosting fast adversarial training with learnable adversarial initialization (TIP2022)☆29Updated 2 years ago
- Triangle Attack: A Query-efficient Decision-based Adversarial Attack (ECCV 2022)☆17Updated 3 years ago