A new framework evaluates privacy metrics for synthetic tabular data by inserting controlled risks and testing detection under no-box threat models on public datasets.
Failure modes in machine learning systems
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
REVELIO uncovers interpretable failure modes in VLMs by searching combinatorial concept spaces with diversity-aware beam search and Gaussian-process Thompson sampling, revealing vulnerabilities in autonomous driving and indoor robotics.
citing papers explorer
-
Empirical Evaluation of Structured Synthetic Data Privacy Metrics: Novel experimental framework
A new framework evaluates privacy metrics for synthetic tabular data by inserting controlled risks and testing detection under no-box threat models on public datasets.
-
Revealing Interpretable Failure Modes of VLMs
REVELIO uncovers interpretable failure modes in VLMs by searching combinatorial concept spaces with diversity-aware beam search and Gaussian-process Thompson sampling, revealing vulnerabilities in autonomous driving and indoor robotics.