defense arXiv Feb 4, 2026 · 8w ago
Inkee Jung, Siu Cheong Lau · Boston University
Entropy-based ensemble immunization defense that detects and adapts to adversarial perturbations via hierarchical logifold generations
Input Manipulation Attack vision
We formulate the fundamental laws governing learning dynamics, namely the conservation law and the decrease of total entropy. Within this framework, we introduce an entropy-based lifelong ensemble learning method. We evaluate its effectiveness by constructing an immunization mechanism to defend against transfer-based adversarial attacks on the CIFAR-10 dataset. Compared with a naive ensemble formed by simply averaging models specialized on clean and adversarial samples, the resulting logifold achieves higher accuracy in most test cases, with particularly large gains under strong perturbations.
cnn Boston University
ML Security Papers