SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1905.11213 · 2019

Provable robustness against all adversarial $l_p$-perturbations for $p\geq 1$

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

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

Abstract

In recent years several adversarial attacks and defenses have been proposed. Often seemingly robust models turn out to be non-robust when more sophisticated attacks are used. One way out of this dilemma are provable robustness guarantees. While provably robust models for specific $l_p$-perturbation models have been developed, we show that they do not come with any guarantee against other $l_q$-perturbations. We propose a new regularization scheme, MMR-Universal, for ReLU networks which enforces robustness wrt $l_1$- and $l_\infty$-perturbations and show how that leads to the first provably robust models wrt any $l_p$-norm for $p\geq 1$.

For agents

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

get_harvested_code_for_paper("1905.11213")
get_code_for_paper("1905.11213")
have("1905.11213")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1905.11213.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1905.11213.svg)](https://syntology.ai/paper/1905.11213)

Connect an agent — have() is free.