conftrace_

model purification

7 papers

Explore in graph

Co-occurring keywords

backdoor attack (385) backdoor defense (55) deep neural network (1803) adversarial training (1262) model security (118) safety assessment (5) trigger pattern (14) trojan attack (23) neural backdoor (3) 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 NIPS 2024
Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples NIPS 2023
Progressive Backdoor Erasing via Connecting Backdoor and Adversarial Attacks CVPR 2023
One-shot Neural Backdoor Erasing via Adversarial Weight Masking NIPS 2022
Training with More Confidence: Mitigating Injected and Natural Backdoors During Training NIPS 2022
Adversarial Neuron Pruning Purifies Backdoored Deep Models NIPS 2021