SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2112.14232 · 2021

Constrained Gradient Descent: A Powerful and Principled Evasion Attack Against Neural Networks

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

We propose new, more efficient targeted white-box attacks against deep neural networks. Our attacks better align with the attacker's goal: (1) tricking a model to assign higher probability to the target class than to any other class, while (2) staying within an $ε$-distance of the attacked input. First, we demonstrate a loss function that explicitly encodes (1) and show that Auto-PGD finds more attacks with it. Second, we propose a new attack method, Constrained Gradient Descent (CGD), using a refinement of our loss function that captures both (1) and (2). CGD seeks to satisfy both attacker objectives -- misclassification and bounded $\ell_{p}$-norm -- in a principled manner, as part of the optimization, instead of via ad hoc post-processing techniques (e.g., projection or clipping). We show that CGD is more successful on CIFAR10 (0.9--4.2%) and ImageNet (8.6--13.6%) than state-of-the-art attacks while consuming less time (11.4--18.8%). Statistical tests confirm that our attack outperforms others against leading defenses on different datasets and values of $ε$.

For agents

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

get_harvested_code_for_paper("2112.14232")
get_code_for_paper("2112.14232")
have("2112.14232")

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

curl https://syntology.ai/api/ran/2112.14232.json

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

[![Syntology run record](https://syntology.ai/api/ran/2112.14232.svg)](https://syntology.ai/paper/2112.14232)

Connect an agent — have() is free.