Skip to content
conftrace_

selective training

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

poisoned data isolation (1) clean model (1) neural network (1) pre-trained language model (1) language model (1) adversarial perturbation (1) adversarial defense (1) deep neural network (1) backdoor attack (1) adversarial training (1)

Papers

Progressive Poisoned Data Isolation for Training-Time Backdoor Defense AAAI 2024 RoAST: Robustifying Language Models via Adversarial Perturbation with Selective Training EMNLP 2023