AI Paper Atlas

Research map / Time series / Long-term forecasting

Beyond Immediate Activation: Temporally Decoupled Backdoor Attacks on Time Series Forecasting

Zhixin Liu, Xuanlin Liu, Sihan Xu, Yaqiong Qiao, Ying Zhang, Xiangrui Cai

AAAI 2026 · Time series › Long-term forecasting · approach: Graph-based multivariate forecasting · 0 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
add position guidance matrix (Gaussian prior on target position) to the trigger generator (ablation)TDBA-Inv · ablation, aggregate over datasetsattacked-position MAE M_p^a: 35.34 -> 18.25Improved
add position guidance matrix to the trigger generator (ablation)TDBA-Gcn · ablation, aggregate over datasetsattacked-position MAE M_p^a: 30.64 -> 16.94Improved
add position-aware optimization objective instead of plain MAE regression (ablation)TDBA-Inv · ablation, aggregate over datasetsattacked-position MAE M_p^a: 29.48 -> 18.25Improved
add position-aware optimization objective instead of plain MAE regression (ablation)TDBA-Gcn · ablation, aggregate over datasetsunaffected-position MAE M_p^c: 21.44 -> 17.40Improved
use TDBA over BackTime for delayed asynchronous target activationTDBA · Weather (avg)attacked-position MAE M_p^a: 23.22 -> 3.48Improved
use TDBA over BackTime on PEMS08TDBA-Gcn · PEMS08attacked-position MAE M_p^a: 25.10 -> 17.52Improved
use TDBA-Gcn instead of BackTime on ETTh1TDBA-Gcn · ETTh1attacked-position MAE M_p^a: 2.74 -> 2.90Hurt
use TDBA under different target pattern shapesTDBA-GCN · PEMS03 Autoformer upward trendattacked-position MAE M_p^a: 20.04 -> 17.70Improved
stealthiness check with USAD anomaly detectionTDBA · PEMS03, PEMS04, PEMS08AUC-ROC: BackTime 0.5747 -> TDBA-Inv 0.4949 on PEMS04Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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