SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2209.07235 · NeurIPS · 2022

Sound and Complete Verification of Polynomial Networks

Fanghui Liu, Volkan Cevher, Elias Rocamora

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 2 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
megaelius/pnverification canonical 1 of 2
FunctionStatusWhere it lives
get_norm Ran megaelius/pnverification/utils_PN.py
code served (permissive licence) · get_code("43a210cd6de06fe2")
from_CCP_Conv_to_CCP Not yet run megaelius/pnverification/utils_PN.py
code served (permissive licence) · get_code("58688cbe43a461a3")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Polynomial Networks (PNs) have demonstrated promising performance on face and image recognition recently. However, robustness of PNs is unclear and thus obtaining certificates becomes imperative for enabling their adoption in real-world applications. Existing verification algorithms on ReLU neural networks (NNs) based on classical branch and bound (BaB) techniques cannot be trivially applied to PN verification. In this work, we devise a new bounding method, equipped with BaB for global convergence guarantees, called Verification of Polynomial Networks or VPN for short. One key insight is that we obtain much tighter bounds than the interval bound propagation (IBP) and DeepT-Fast [Bonaert et al., 2021] baselines. This enables sound and complete PN verification with empirical validation on MNIST, CIFAR10 and STL10 datasets. We believe our method has its own interest to NN verification. The source code is publicly available at https://github.com/megaelius/PNVerification.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2209.07235")
get_code_for_paper("2209.07235")
have("2209.07235")

Connect an agent — have() is free.