AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

Practical Adversarial Attacks on Spatiotemporal Traffic Forecasting Models

Fan Liu, Hao Liu, Wenzhao Jiang

NeurIPS 2022 · Adversarial robustness and security › Attacks on text and graphs · approach: Attacks and defenses in sequential settings · 15 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
Use TDNS to select victim nodes instead of random selection (ablation)STPGD-TDNS · PeMS-BAY, grey-boxG-MAE: 5.9024 -> 6.1329Improved
Use STPGD rather than vanilla PGD noise on selected nodes (ablation)STPGD-TDNS · PeMS-BAY, grey-boxG-MAE: 4.5969 -> 6.1329Improved
Use TDNS rather than random node selection (ablation)STPGD-TDNS · PeMS-BAY, white-boxG-MAE: 6.1477 -> 6.4709Improved
Apply STPGD-TDNS instead of leaving the model un-attackedGraphWaveNet · PeMS-BAY, grey-boxG-MAE: 1.975 -> 6.1329Hurt
Apply STMIM-TDNS instead of leaving the model un-attackedGraphWaveNet · METR-LA, grey-boxG-MAE: 6.3504 -> 7.9381Hurt
Use STPGD-TDNS instead of the strongest listed baselineGraphWaveNet · PeMS-BAY, grey-boxG-MAE: 5.5321 -> 6.1329Improved
Use PGD-TDNS rather than PGD-Centrality victim selectionGraphWaveNet · PeMS-BAY, black-boxG-MAE: 4.4859 -> 4.5636Improved
Train using adversarial examples generated by STPGD-TDNS rather than standard adversarial trainingGraphWaveNet · PeMS-BAY, white-box defense under PGD-RandomG-MAE: 2.5436 (0.0249) -> 2.4695 (0.0036)Improved
Increase the victim-node budgetSTPGD-TDNS · PeMS-BAYG-RMSEImproved
Increase perturbation budgetSTPGD-TDNS · PeMS-BAYG-RMSEMixed
Increase batch sizeSTPGD-TDNS · PeMS-BAYG-RMSEMixed
Increase the forecasting time intervalSTPGD-TDNS · PeMS-BAY, 5 to 60 minutesG-MAE: 3.9458 -> 6.1329Mixed

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