Chameleon recovers CPS from memory corruption attacks by swapping compromised compartments with ML surrogates that approximate original behavior (avg R²=0.96) while avoiding the same vulnerabilities.
Learning long-term dependen- cies with gradient descent is difficult,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
ELMP performs data-efficient self-supervised adaptation of neural motion planners via analytical policy gradients and point-cloud tool encoding, raising success from 57.3% zero-shot to 89.8% in unseen environments.
citing papers explorer
-
Chameleon: Recovering Cyber-Physical Systems from Memory Corruption Attacks via ML Surrogates
Chameleon recovers CPS from memory corruption attacks by swapping compromised compartments with ML surrogates that approximate original behavior (avg R²=0.96) while avoiding the same vulnerabilities.
-
ELMP: Efficient Learning for Motion Planning via Analytical Policy Gradients
ELMP performs data-efficient self-supervised adaptation of neural motion planners via analytical policy gradients and point-cloud tool encoding, raising success from 57.3% zero-shot to 89.8% in unseen environments.