Skip to content
Back to skills

Towards White Box Deep Learning

ASecurity

**arXiv ID:** 2403.09863 **Authors:** Maciej Satkiewicz **Published:** 2024-03-14T20:50:03Z **Abstract:** Deep neural networks learn fragile "shortcut" features, rendering them difficult to interpret (black box) and vulnerable to adversarial attacks. This paper proposes semantic features as a general architectural solution to this problem. The main idea is to make features locality-sensitive in the adequate semantic topology of the domain, thus introducing a strong regularization. The proof o...

  • 3 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 11, 2026
toolsgit

Security analysis

A100/100

Scanned September 11, 2026

npx -y skills add hiyenwong/ai_collection --skill towards-white-box-deep-learning --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Towards White Box Deep Learning?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Towards White Box Deep Learning
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/hiyenwong-towards-white-box-deep-learning/badge)](https://www.skillsdirectory.com/skills/hiyenwong-towards-white-box-deep-learning)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
# Towards White Box Deep Learning

**arXiv ID:** 2403.09863
**Authors:** Maciej Satkiewicz
**Published:** 2024-03-14T20:50:03Z
**Abstract:**
Deep neural networks learn fragile "shortcut" features, rendering them difficult to interpret (black box) and vulnerable to adversarial attacks. This paper proposes semantic features as a general architectural solution to this problem. The main idea is to make features locality-sensitive in the adequate semantic topology of the domain, thus introducing a strong regularization. The proof of concept network is lightweight, inherently interpretable and achieves almost human-level adversarial test metrics - with no adversarial training! These results and the general nature of the approach warrant further research on semantic features. The code is available at https://github.com/314-Foundation/white-box-nn

## Skill Description

This skill is generated from the arXiv paper: Towards White Box Deep Learning (2403.09863).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:2403.09863](http://arxiv.org/abs/2403.09863v5)

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in tools →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.