# UnAct: Gradient-Free Unlearning via Targeted Activation Intervention > Source: > Published: 2026-10-07 01:30:19+00:00 Machine unlearning seeks to remove the influence of designated training data from a trained model without retraining from scratch. Retrain-free methods such as Selective Synaptic Dampening (SSD) and its label-free variant LFSSD avoid full retraining but still require backpropagation and parameter im