Universal Approximation with Certified Networks
Training neural networks to be certifiably robust is critical to ensure their safety against adversarial attacks. However, it is currently very difficult to train a neural network that is both accurate and certifiably robust. In this work we take a step towards addressing this challenge. We prove that for every continuous function $f$, there exists a network $n$ such that: (i) $n$ approximates $f$ arbitrarily close, and (ii) simple interval bound propagation of a region $B$ through $n$ yields a result that is arbitrarily close to the optimal output of $f$ on $B$. Our result can be seen as a Universal Approximation Theorem for interval-certified ReLU networks. To the best of our knowledge, this is the first work to prove the existence of accurate, interval-certified networks.
Code (1)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Universal Lipschitz Approximation in Bounded Depth Neural Networks
Adversarial attacks against machine learning models are a rather hefty obstacle to our increasing reliance on these models. Due to this, provably robust (certified) machine learning models are a major topic of interest. …
BIG-bench Machine LearningGeneralized Universal Approximation for Certified Networks
To certify safety and robustness of neural networks, researchers have successfully applied abstract interpretation, primarily using interval bound propagation. To understand the power of interval bounds, we present the a…
UniCR: Universally Approximated Certified Robustness via Randomized Smoothing
We study certified robustness of machine learning classifiers against adversarial perturbations. In particular, we propose the first universally approximated certified robustness (UniCR) framework, which can approximate …
SpecSphere: Dual-Pass Spectral-Spatial Graph Neural Networks with Certified Robustness
We introduce SpecSphere, the first dual-pass spectral-spatial GNN that certifies every prediction against both $\ell\_{0}$ edge flips and $\ell\_{\infty}$ feature perturbations, adapts to the full homophily-heterophily s…
Node ClassificationCross-Input Certified Training for Universal Perturbations
Existing work in trustworthy machine learning primarily focuses on single-input adversarial perturbations. In many real-world attack scenarios, input-agnostic adversarial attacks, e.g. universal adversarial perturbations…