# Robust Attacks against Multiple Classifiers

Source: [Robust Attacks against Multiple Classifiers](<https://www.sota2.com/research/paper/68fa65df1e209131cea0cfe5>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:37:37.790Z

Authors: Juan C. Perdomo, Yaron Singer

Published: 2019-06-06T21:06:28.000Z

## Abstract

We address the challenge of designing optimal adversarial noise algorithms for settings where a learner has access to multiple classifiers. We demonstrate how this problem can be framed as finding strategies at equilibrium in a two-player, zero-sum game between a learner and an adversary. In doing so, we illustrate the need for randomization in adversarial attacks. In order to compute Nash equilibrium, our main technical focus is on the design of best response oracles that can then be implemented within a Multiplicative Weights Update framework to boost deterministic perturbations against a set of models into optimal mixed strategies. We demonstrate the practical effectiveness of our approach on a series of image classification tasks using both linear classifiers and deep neural networks.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1906.02816>)

[PDF](<https://arxiv.org/pdf/1906.02816.pdf>)