विधियों की तुलना करें

	एडवरसैरियल ट्रेनिंग (Adversarial Training)	आउट-ऑफ-डिस्ट्रीब्यूशन डिटेक्शन
क्षेत्र	गहन अधिगम	मशीन अधिगम
परिवार	Machine learning	Machine learning
उद्भव वर्ष	2018	2017
प्रवर्तक	Aleksander Madry et al.	Hendrycks & Gimpel
प्रकार	Robust optimization training procedure	Reliability and safety method for neural networks
मौलिक स्रोत	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).	Hendrycks, D., & Gimpel, K. (2017). A baseline for detecting misclassified and out-of-distribution examples in neural networks. International Conference on Learning Representations.
उपनाम	Min-Max Robust Training, PGD Adversarial Training, Robust Empirical Risk Minimization, Hasımsal Eğitim	OOD Detection, Novelty Detection, Open-Set Recognition, Dağılım Dışı Tespit
संबंधित	3	3
सारांश	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.	Out-of-Distribution (OOD) detection is a set of techniques that identify when a deployed machine learning model receives inputs that differ significantly from its training data distribution. Introduced as a formal problem by Hendrycks and Gimpel in 2017, these methods enable models to flag unfamiliar inputs rather than silently produce unreliable predictions, making them foundational to trustworthy and safe AI deployment in high-stakes domains.