On existence, uniqueness and scalability of adversarial robustness measures for AI classifiers
Simply-verifiable mathematical conditions for existence, uniqueness and explicit analytical computation of minimal adversarial paths (MAP) and minimal adversarial distances (MAD) for (locally) uniquely-invertible classifiers, for generalized linear models (GLM), and for entropic AI (EAI) are formulated and proven. Practical computation of MAP and MAD, their comparison and interpretations for various classes of AI tools (for neuronal networks, boosted random forests, GLM and EAI) are demonstrated on the common synthetic benchmarks: on a double Swiss roll spiral and its extensions, as well as on the two biomedical data problems (for the health insurance claim predictions, and for the heart attack lethality classification). On biomedical applications it is demonstrated how MAP provides unique minimal patient-specific risk-mitigating interventions in the predefined subsets of accessible control variables.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial RobustnessMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Invariance and Inverse Stability under ReLU
We flip the usual approach to study invariance and robustness of neural networks by considering the non-uniqueness and instability of the inverse mapping. We provide theoretical and numerical results on the inverse of Re…
Hellinger loss function for Generative Adversarial Networks
We propose Hellinger-type loss functions for training Generative Adversarial Networks (GANs), motivated by the boundedness, symmetry, and robustness properties of the Hellinger distance. We define an adversarial objectiv…
Rates of Convergence of Generalised Variational Inference Posteriors under Prior Misspecification
We prove rates of convergence and robustness to prior misspecification within a Generalised Variational Inference (GVI) framework with bounded divergences. This addresses a significant open challenge for GVI and Federate…
A Distributional Robustness Perspective on Adversarial Training with the $\infty$-Wasserstein Distance
While ML tools are becoming increasingly used in industrial applications, adversarial examples remain a critical flaw of neural networks. These imperceptible perturbations of natural inputs are, on average, misclassified…
Existence of a Competitive Equilibrium with Substitutes, with Applications to Matching and Discrete Choice Models
We propose new results for the existence and uniqueness of a general nonparametric and nonseparable competitive equilibrium with substitutes. These results ensure the invertibility of a general competitive system. The ex…
Discrete Choice Models