conftrace_

model purification

7 papers

Explore in graph

Co-occurring keywords · papers mentioning both

backdoor attack (5) backdoor defense (5) deep neural network (4) adversarial training (2) model security (2) safety assessment (1) trigger pattern (1) trojan attack (1) neural backdoor (1) adversarial weight masking (1)

Papers

Cut the Deadwood Out: Backdoor Purification via Guided Module Substitution EMNLP 2025 Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense NeurIPS 2024 Progressive Backdoor Erasing via Connecting Backdoor and Adversarial Attacks CVPR 2023 Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples NeurIPS 2023 One-shot Neural Backdoor Erasing via Adversarial Weight Masking NeurIPS 2022 Training with More Confidence: Mitigating Injected and Natural Backdoors During Training NeurIPS 2022 Adversarial Neuron Pruning Purifies Backdoored Deep Models NeurIPS 2021