A hybrid randomized smoothing method yields a closed-form certificate for joint discrete-continuous perturbations that generalizes prior Gaussian and discrete smoothing approaches.
Membership Inference Attacks on Large-Scale Models: A Survey
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
AI security research shows biased attack-to-defense ratios, with attacks evaluated under favorable conditions and defenses under stricter standards, resulting in a call to better incentivize defense work.
citing papers explorer
-
Certified Robustness under Heterogeneous Perturbations via Hybrid Randomized Smoothing
A hybrid randomized smoothing method yields a closed-form certificate for joint discrete-continuous perturbations that generalizes prior Gaussian and discrete smoothing approaches.
-
AI Security Research Should Better Incentivize Defense Research
AI security research shows biased attack-to-defense ratios, with attacks evaluated under favorable conditions and defenses under stricter standards, resulting in a call to better incentivize defense work.