Compositional robustness testing for vision models
-
Updated
May 28, 2026 - Python
#
autoattack
Here are 4 public repositories matching this topic...
Evasion attacks (FGSM, PGD, C&W, APGD, Square, AutoAttack-style ensemble), adversarial training (PGD-AT, TRADES, FGSM-RS) and randomized smoothing certification on the full CIFAR-10 test set, checked against torchattacks 3.5.1 and mapped to MITRE ATLAS v2026.10
pytorch cifar10 adversarial-attacks ai-security adversarial-training adversarial-robustness randomized-smoothing certified-robustness mitre-atlas autoattack
-
Updated
Nov 8, 2026 - Python
Black-Box Neural Network Hardening Through Surrogate Model Defense Integration
computer-vision deep-learning pytorch knowledge-distillation model-extraction ai-safety wgan-gp onnx machine-learning-security surrogate-models adversarial-training adversarial-robustness adaptive-attacks black-box-defense autoattack robustbench dataset-synthesis defense-transfer
-
Updated
Mar 4, 2026 - Jupyter Notebook
Controlled PyTorch comparison of standard and adversarial training on GTSRB, with PGD, AutoAttack, reproducible evaluation, and measured accuracy–robustness trade-offs.
pytorch traffic-sign-classification gtsrb wide-resnet adversarial-training adversarial-robustness projected-gradient-descent autoattack
-
Updated
Sep 13, 2026 - Python
Add this topic to your repo
To associate your repository with the autoattack topic, visit your repo's landing page and select "manage topics."