Сравнение на методи

	Трениране с противникови атаки	Генеративна състезателна мрежа
Област	Дълбоко обучение	Дълбоко обучение
Семейство	Machine learning	Machine learning
Година на възникване	2018	2014
Създател	Aleksander Madry et al.	Goodfellow, I. et al.
Тип	Robust optimization training procedure	Generative deep learning (adversarial two-network game)
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).	Goodfellow, I. et al. (2014). Generative Adversarial Nets. NeurIPS.
Други названия	Min-Max Robust Training, PGD Adversarial Training, Robust Empirical Risk Minimization, Hasımsal Eğitim	Üretici Çekişmeli Ağ (GAN), GAN, generative adversarial nets, adversarial network
Свързани	3	4
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.	A Generative Adversarial Network (GAN), introduced by Ian Goodfellow and colleagues in 2014, produces realistic synthetic data through the competition of two neural networks — a generator and a discriminator. It is widely used for image synthesis, data augmentation, and distribution estimation.