DIPBox is the first multi-scale testing framework for detecting adversarial dataset regeneration via four similarity metrics, backed by learning-theoretic analysis of utility-divergence trade-offs.
arXiv preprint arXiv:2202.06438 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Temporal correlations from lazy random walks enable efficient SGD learning of k-juntas via temporal-difference loss on ReLU networks, achieving linear sample complexity in d.
citing papers explorer
-
DIPBox: A Multi-scale Testing Framework for Tracking Dataset Regeneration
DIPBox is the first multi-scale testing framework for detecting adversarial dataset regeneration via four similarity metrics, backed by learning-theoretic analysis of utility-divergence trade-offs.
-
The Benefits of Temporal Correlations: SGD Learns k-Juntas from Random Walks Efficiently
Temporal correlations from lazy random walks enable efficient SGD learning of k-juntas via temporal-difference loss on ReLU networks, achieving linear sample complexity in d.