SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2009.09612 · 2020

Improving Ensemble Robustness by Collaboratively Promoting and Demoting Adversarial Robustness

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

Ensemble-based adversarial training is a principled approach to achieve robustness against adversarial attacks. An important technique of this approach is to control the transferability of adversarial examples among ensemble members. We propose in this work a simple yet effective strategy to collaborate among committee models of an ensemble model. This is achieved via the secure and insecure sets defined for each model member on a given sample, hence help us to quantify and regularize the transferability. Consequently, our proposed framework provides the flexibility to reduce the adversarial transferability as well as to promote the diversity of ensemble members, which are two crucial factors for better robustness in our ensemble approach. We conduct extensive and comprehensive experiments to demonstrate that our proposed method outperforms the state-of-the-art ensemble baselines, at the same time can detect a wide range of adversarial examples with a nearly perfect accuracy. Our code is available at: https://github.com/tuananhbui89/Crossing-Collaborative-Ensemble.

For agents

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

get_harvested_code_for_paper("2009.09612")
get_code_for_paper("2009.09612")
have("2009.09612")

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

curl https://syntology.ai/api/ran/2009.09612.json

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

[![Syntology run record](https://syntology.ai/api/ran/2009.09612.svg)](https://syntology.ai/paper/2009.09612)

Connect an agent — have() is free.