SuperDP refutes ε-DP via simultaneous synthesis of input pairs and witness functions using upper expectation supermartingales and lower expectation submartingales, delivering the first fully automated, sound, and semi-complete method applicable to both discrete and continuous stochastic mechanisms.
Calvert, and Luca Laurenti
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
A scalable verification framework for neural control barrier functions uses linear bound propagation on network gradients combined with McCormick relaxations to certify safety conditions for control-affine systems.
citing papers explorer
-
SuperDP: Differential Privacy Refutation via Supermartingales
SuperDP refutes ε-DP via simultaneous synthesis of input pairs and witness functions using upper expectation supermartingales and lower expectation submartingales, delivering the first fully automated, sound, and semi-complete method applicable to both discrete and continuous stochastic mechanisms.
-
Scalable Verification of Neural Control Barrier Functions Using Linear Bound Propagation
A scalable verification framework for neural control barrier functions uses linear bound propagation on network gradients combined with McCormick relaxations to certify safety conditions for control-affine systems.