Papers › Non-Negative Networks Against Adversarial Attacks

Non-Negative Networks Against Adversarial Attacks

15 Jun 2018arXiv:1806.06108archive 2025-07-28

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

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

endgameinc/malware_evasion_competition mentioned on GitHubpytorchAGPL-3.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Binary ClassificationClassificationGeneral ClassificationImage ClassificationSpam detectionimage-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections