Metodbevispost

Adversarial Training

Adversarial Training is a robust optimization procedure for deep neural networks in which the model is trained not on clean data alone but on worst-case perturbed inputs crafted during training. Formalized by Madry et al. (2018) as a min-max saddle-point problem, the method uses Projected Gradient Descent (PGD) to generate strong adversarial examples within a bounded Lp perturbation set before each gradient update, forcing the network to learn decision boundaries that are stable under such perturbations.

Sources recorded, not reviewed

Källpost

Citat kopierade ordagrant från metodens källpost. Ingen verifiering på källnivå härleds från dem.

Adversarial Training (Robust Optimization for DL)

Taxonomisk metodpost · ml-model / deep-learning

Madry, A., Makelov, A., Schmidt, L., Tsipras, D., & Vladu, A. (2018). Towards deep learning models resistant to adversarial attacks. International Conference on Learning Representations (ICLR). · URL

Öppna fullständig metod

Kuraterade påståenden

Påståenden lagrade i bevisloggen, var och en med sin egen bedömning.

Inga kuraterade påståenden ännu

Denna vy hittar inte på en påståendebedömning när loggen saknar en.

Relaterade metoder

Genererade från metodgrafen och visade som maskinföreslagna relationer – inga bevispåståenden härleds.

Taxonomic bucketData Augmentationmachine-suggested · Relational suggestion, not evidence.Same method familyGenerative Adversarial Networkmachine-suggested · Relational suggestion, not evidence.Same method familyOut-of-Distribution Detectionmachine-suggested · Relational suggestion, not evidence.