conftrace_

adversarial attack defense

3 papers

Explore in graph

Co-occurring keywords

model utility preservation (3) membership inference (114) data-efficient learning (53) point cloud classification (57) implicit gradient (6) pretrained classifier (3) privacy-preserving model (2) concept forgetting (4) multimodal language model (76) right to be forgotten (24)

Papers

Single Image Unlearning: Efficient Machine Unlearning in Multimodal Large Language Models NIPS 2024
DE-CROP: Data-Efficient Certified Robustness for Pretrained Classifiers WACV 2023
Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks With Implicit Gradients CVPR 2022