Záznam dôkazov metódy

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

Zdrojový záznam

Citácie skopírované doslovne zo zdrojového záznamu metódy. Nevyplýva z nich žiadne overenie na úrovni tvrdenia.

Adversarial Training (Robust Optimization for DL)

Taxonomický záznam metódy · 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

Otvoriť celú metódu

Spracované tvrdenia

Tvrdenia uložené v registri dôkazov, každé s vlastným hodnotením.

Zatiaľ žiadne spracované tvrdenia

Tento pohľad nevymýšľa hodnotenie tvrdenia, ak register žiadne nemá.

Súvisiace metódy

Vygenerované z grafu metód a zobrazené ako vzťahy navrhnuté strojom – nevyplýva z nich žiadne tvrdenie o dôkaze.

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.