Skip to content
conftrace_

backdoor attack defense

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

backdoor attack (2) neural network security (2) clean-label recovery (1) outlier word detection (1) textual backdoor attack (1) neural network (1) self-supervised representation learning (1) model sparsification (1) approximate unlearning (1) model sparsity (1)

Papers

Seal Your Backdoor with Variational Defense ICCV 2025 Model Sparsity Can Simplify Machine Unlearning NeurIPS 2023 Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork NeurIPS 2022 ONION: A Simple and Effective Defense Against Textual Backdoor Attacks EMNLP 2021