Сравнение на методи

	Трениране с противникови атаки	Трансферно обучение
Област	Дълбоко обучение	Машинно обучение
Семейство	Machine learning	Machine learning
Година на възникване	2018	2010 (formalized); 1990s (early roots)
Създател	Aleksander Madry et al.	Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing)
Тип	Robust optimization training procedure	Learning paradigm
Основополагащ източник	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).	Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.
Други названия	Min-Max Robust Training, PGD Adversarial Training, Robust Empirical Risk Minimization, Hasımsal Eğitim	TL, domain adaptation, fine-tuning, pre-trained model adaptation
Свързани	3	3
Резюме	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.	Transfer learning is a machine learning paradigm in which knowledge gained from training a model on a source task or domain is reused to improve learning on a different but related target task or domain. It is especially powerful when labeled data for the target task is scarce, and it underlies most modern deep learning applications in computer vision, natural language processing, and beyond.