# Non-Negative Networks Against Adversarial Attacks

Source: [Non-Negative Networks Against Adversarial Attacks](<https://www.sota2.com/research/paper/68fa653b1e209131cea093ad>)

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

Data updated: 2025-10-25T21:22:52.893Z

Authors: William Fleshman, Edward Raff, Jared Sylvester, Steven Forsyth, Mark McLean

Published: 2018-06-15T20:02:57.000Z

## Abstract

Adversarial attacks against neural networks are a problem of considerable importance, for which effective defenses are not yet readily available. We make progress toward this problem by showing that non-negative weight constraints can be used to improve resistance in specific scenarios. In particular, we show that they can provide an effective defense for binary classification problems with asymmetric cost, such as malware or spam detection. We also show the potential for non-negativity to be helpful to non-binary problems by applying it to image classification.

## 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/1806.06108>)

[PDF](<https://arxiv.org/pdf/1806.06108.pdf>)