Skip to content
conftrace_

backdoor removal

7 papers

Explore in graph

Co-occurring keywords · papers mentioning both

backdoor attack (4) adversarial learning (3) trigger inversion (2) backdoor defense (2) adversarial prompt tuning (1) soft token (1) safety backdoor (1) model cloning (1) trojaned model (1) cloning loss (1)

Papers

Activation Space Interventions Can Be Transferred Between Large Language Models ICML 2025 Two Sides of the Same Coin: Learning the Backdoor to Remove the Backdoor AAAI 2025 BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models EMNLP 2024 PromptFix: Few-shot Backdoor Removal via Adversarial Prompt Tuning NAACL 2024 Towards Reliable and Efficient Backdoor Trigger Inversion via Decoupling Benign Features ICLR 2024 MEDIC: Remove Model Backdoors via Importance Driven Cloning CVPR 2023 Adversarial Neuron Pruning Purifies Backdoored Deep Models NeurIPS 2021