AI Paper Atlas

Research map / Adversarial robustness and security / Backdoor and poisoning

DUP: Detection-guided Unlearning for Backdoor Purification in Language Models

Man Hu, Yahui Ding, Yatao Yang, Liangyu Chen, Yanhao Jia, Shuai Zhao

AAAI 2026 · Adversarial robustness and security › Backdoor and poisoning · approach: Detecting poisoned samples · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
select top-k layers by Calinski-Harabasz score instead of all layers (ablation)MS detector · BadNets on SST-2 (BART)AUC (%): 74.73 -> 99.27Improved
use last-half layers instead of first-half layers (ablation)MS detector · BadNets on SST-2 (BERT)AUC (%): 88.10 -> 99.84Improved
add spectral signature score to Mahalanobis distance (ablation)MS detector · BadNets on SST-2 (BART)AUC (%): 85.71 -> 99.27Improved
add spectral signature score (ablation)MS detector · BadNets on SST-2 (LLaMA 3B)AUC (%): 95.61 -> 94.39Hurt
add preservation loss (cross-entropy on clean samples) (ablation)DUP · SST-2 (BERT)CACCImproved
add unlearning loss (KL divergence on detected poisoned samples) (ablation)DUP · SST-2 (BERT)ASRImproved
increase lambda_asr from 1 to 5 (ablation)DUP · SST-2 (BERT)ASRImproved
increase lambda_acc from 1 to 5 (ablation)DUP · SST-2 (BERT)CACCImproved
attacker adds feature-level regularization (adaptive attack) (ablation)DUP · Stylebkd on SST-2 (BERT)ASR (%): 5.81 -> 12.28Hurt
attacker adds feature-level regularization (adaptive attack) (ablation)DUP · AddSent on SST-2 (BERT)ASR (%): 0.22 -> 0No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy