Research

On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,786 papers · 148 categories

Trend · papers per month

count % of corpus

1 result for “RPENNs”

An Empirical Investigation of Randomized Defenses against Adversarial Attackscs.LG

This paper evaluates defenses against adversarial attacks on neural networks.

problem Adversarial attacks can trick DNNs into mis-classifying inputs.

method Scientific evaluation methodology for randomized defenses.

result RPENNs outperformed other defenses against adversarial attacks.

adversarial attacks neural networks randomized defenses evaluation methodology RPENNs

2019-09-12abs ↗pdf ↗