Sign inGet started
Repository · GitHub

eth-sri/diffai

A certifiable defense against adversarial examples by training neural networks to be provably robust

Ownereth-sri
License (as declared)MIT
Stars221
Forks24
Main languagePython
Created8 July 2018
Last updated at source25 July 2024
pythonabstract-interpretationattackdefenseneural-networkpytorchrobust
Embed this entry
<iframe src="https://silytics.si/embed/item/255b4ffe-0b5c-43fb-b928-52bda43e6e13" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

Stars, last 3 days

221 now. Counts as reported by the source, snapshotted daily by Silytics.

More from eth-sri

Silytics shows public metadata from GitHub and links to the original. Information may be incomplete or out of date. Last refreshed 18 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.