ProjGuard monitors agent trajectories with low-dimensional projections to cut unsafe actions from 16% to 3% and raise task completion from 59% to 65% on OS-Harm.
On lines and planes of closest fit to systems of points in space.The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science, 2(11):559–572
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
A domain adaptation framework with spectral feature alignment and K-Medoids clustering after PCA improves unknown attack detection accuracy by up to 49% over baselines and gains another 26% from the clustering step in cross-domain ICS intrusion detection.
Digital twins generate synthetic FMCW radar data for benchmarking quantum SVM against classical RBF SVM on PCA-reduced features, showing modest quantum improvement on UAV classification in noiseless simulation.
citing papers explorer
-
ProjGuard: Safety Monitoring for Computer-Use Agents via Low-Dimensional Projections
ProjGuard monitors agent trajectories with low-dimensional projections to cut unsafe actions from 16% to 3% and raise task completion from 59% to 65% on OS-Harm.
-
Clustering-Enhanced Domain Adaptation for Cross-Domain Intrusion Detection in Industrial Control Systems
A domain adaptation framework with spectral feature alignment and K-Medoids clustering after PCA improves unknown attack detection accuracy by up to 49% over baselines and gains another 26% from the clustering step in cross-domain ICS intrusion detection.
-
Digital twins for compact hybrid quantum classical learning in FMCW radar detection
Digital twins generate synthetic FMCW radar data for benchmarking quantum SVM against classical RBF SVM on PCA-reduced features, showing modest quantum improvement on UAV classification in noiseless simulation.