SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2211.15030 · 2022

Imperceptible Adversarial Attack via Invertible 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

Adding perturbations via utilizing auxiliary gradient information or discarding existing details of the benign images are two common approaches for generating adversarial examples. Though visual imperceptibility is the desired property of adversarial examples, conventional adversarial attacks still generate traceable adversarial perturbations. In this paper, we introduce a novel Adversarial Attack via Invertible Neural Networks (AdvINN) method to produce robust and imperceptible adversarial examples. Specifically, AdvINN fully takes advantage of the information preservation property of Invertible Neural Networks and thereby generates adversarial examples by simultaneously adding class-specific semantic information of the target class and dropping discriminant information of the original class. Extensive experiments on CIFAR-10, CIFAR-100, and ImageNet-1K demonstrate that the proposed AdvINN method can produce less imperceptible adversarial images than the state-of-the-art methods and AdvINN yields more robust adversarial examples with high confidence compared to other adversarial attacks.

For agents

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

get_harvested_code_for_paper("2211.15030")
get_code_for_paper("2211.15030")
have("2211.15030")

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

curl https://syntology.ai/api/ran/2211.15030.json

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

[![Syntology run record](https://syntology.ai/api/ran/2211.15030.svg)](https://syntology.ai/paper/2211.15030)

Connect an agent — have() is free.