TimeGuard employs channel-wise pool training initialized with time-aware criteria and distance-regularized loss selection to defend time series forecasting against backdoor attacks, improving robustness by 1.96x while keeping clean performance within 5%.
2021 10th International Conference on Internet Computing for Science and Engineering , pages=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting
TimeGuard employs channel-wise pool training initialized with time-aware criteria and distance-regularized loss selection to defend time series forecasting against backdoor attacks, improving robustness by 1.96x while keeping clean performance within 5%.