SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.04379 · 2023

Et Tu Certifications: Robustness Certificates Yield Better Adversarial Examples

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 guaranteeing the absence of adversarial examples in an instance's neighbourhood, certification mechanisms play an important role in demonstrating neural net robustness. In this paper, we ask if these certifications can compromise the very models they help to protect? Our new \emph{Certification Aware Attack} exploits certifications to produce computationally efficient norm-minimising adversarial examples $74 \%$ more often than comparable attacks, while reducing the median perturbation norm by more than $10\%$. While these attacks can be used to assess the tightness of certification bounds, they also highlight that releasing certifications can paradoxically reduce security.

For agents

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

get_harvested_code_for_paper("2302.04379")
get_code_for_paper("2302.04379")
have("2302.04379")

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

curl https://syntology.ai/api/ran/2302.04379.json

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

[![Syntology run record](https://syntology.ai/api/ran/2302.04379.svg)](https://syntology.ai/paper/2302.04379)

Connect an agent — have() is free.