Krahasoni metodat

	Trajnim i kundërshtueshëm	Rrjeti kundërshtar gjenerues
Fusha	Mësimi i thellë	Mësimi i thellë
Familja	Machine learning	Machine learning
Viti i origjinës	2018	2014
Krijuesi	Aleksander Madry et al.	Goodfellow, I. et al.
Lloji	Robust optimization training procedure	Generative deep learning (adversarial two-network game)
Burimi themelues	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.
Emërtime të tjera	Min-Max Robust Training, PGD Adversarial Training, Robust Empirical Risk Minimization, Hasımsal Eğitim	Üretici Çekişmeli Ağ (GAN), GAN, generative adversarial nets, adversarial network
Të lidhura	3	4
Përmbledhja	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.