ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 1903.08778
19
57

Provable Certificates for Adversarial Examples: Fitting a Ball in the Union of Polytopes

20 March 2019
Matt Jordan
Justin Lewis
A. Dimakis
    AAML
ArXivPDFHTML
Abstract

We propose a novel method for computing exact pointwise robustness of deep neural networks for all convex ℓp\ell_pℓp​ norms. Our algorithm, GeoCert, finds the largest ℓp\ell_pℓp​ ball centered at an input point x0x_0x0​, within which the output class of a given neural network with ReLU nonlinearities remains unchanged. We relate the problem of computing pointwise robustness of these networks to that of computing the maximum norm ball with a fixed center that can be contained in a non-convex polytope. This is a challenging problem in general, however we show that there exists an efficient algorithm to compute this for polyhedral complices. Further we show that piecewise linear neural networks partition the input space into a polyhedral complex. Our algorithm has the ability to almost immediately output a nontrivial lower bound to the pointwise robustness which is iteratively improved until it ultimately becomes tight. We empirically show that our approach generates distance lower bounds that are tighter compared to prior work, under moderate time constraints.

View on arXiv
Comments on this paper