Latest posts tagged with #AdversarialTraining on Bluesky
Adversarial Training Boosts Security of Hyperspectral Image Classification
AT‑RA adversarial training raised hyperspectral classifier robustness 21.34% on AutoAttack and 18.78% on PGD‑50, while improving benign accuracy by 2.68%. Read more: getnews.me/adversarial-training-boo... #hyperspectral #adversarialtraining
Dual-Level Defense Routing Boosts Continual Adversarial Training
Dual‑level Defense Routing (DDeR) with Pseudo‑task Substitution Training improves adversarial defense; experiments report higher accuracy and reduced forgetting. Read more: getnews.me/dual-level-defense-routi... #adversarialtraining #defenserouting
Adversarial Training Ineffective on Compressed Datasets
Compressed condensation datasets lose adversarial robustness; new Minimal Finite Covering restores robust accuracy on benchmark image classification. Read more: getnews.me/adversarial-training-ine... #adversarialtraining #datasetcondensation
FairAT Boosts AI Security and Fairness by Targeting Its Weakest Links 🔐🤖📊 www.azoai.com/news/2025041... #AI #Cybersecurity #MachineLearning #Fairness #DeepLearning #EthicalAI #AdversarialTraining #TrustworthyAI #DataScience #RobustAI
