Certified PEFTSmoothing: Parameter-Efficient Fine-Tuning with Randomized Smoothing

arXiv:2404.05350v1 Announce Type: new
Abstract: Randomized smoothing is the primary certified robustness method for accessing the robustness of deep learning models to adversarial perturbations in the l2-norm, by adding isotropic Gaussian noise to the input image and returning the majority votes over the base classifier. Theoretically, it provides a certified norm bound, ensuring predictions of adversarial examples are stable within this bound. A notable constraint limiting widespread adoption is the necessity to retrain base models entirely from scratch to attain …

abstract adversarial arxiv classifier cs.cr cs.lg deep learning fine-tuning image noise norm robustness type