ConceptGradient Ascent
Gradient Ascent
An optimization direction opposite to gradient descent, which maximizes the loss function to eliminate a model's memory of specific data. It is a commonly used baseline method in the machine unlearning domain.
Timeline (last 90 days)
Oct 15
Adversarial examples exploit the fragility of the model's decision boundary in high-dimensional space; the network's robustness mechanisms (such as normalization and Dropout) are effective against random noise but almost ineffective against adversarial perturbations, because the perturbation direction is exactly the gradient ascent direction.
Unverified50%