Papers › Adversarial Training Versus Weight Decay

Adversarial Training Versus Weight Decay

10 Apr 2018arXiv:1804.03308archive 2025-07-28

Angus Galloway, Thomas Tanay, Graham W. Taylor

Performance-critical machine learning models should be robust to input perturbations not seen during training. Adversarial training is a method for improving a model's robustness to some perturbations by including them in the training process, but this tends to exacerbate other vulnerabilities of the model. The adversarial training framework has the effect of translating the data with respect to the cost function, while weight decay has a scaling effect. Although weight decay could be considered a crude regularization technique, it appears superior to adversarial training as it remains stable over a broader range of regimes and reduces all generalization errors. Equipped with these abstractions, we provide key baseline results and methodology for characterizing robustness. The two approaches can be combined to yield one small model that demonstrates good robustness to several white-box attacks associated with different metrics.

PaperPDFCode

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

Code

AngusG/tflite-android-black-box-attacks officialmentioned in papertf 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.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Weight Decay

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