GitHub / arturmiller / adversarial_ml_ctf
This repository is a CTF challenge, showing a security flaw in most (all?) common artificial neural networks. They are vulnerable for adversarial images.
JSON API: http://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/arturmiller%2Fadversarial_ml_ctf
PURL: pkg:github/arturmiller/adversarial_ml_ctf
Stars: 5
Forks: 1
Open issues: 0
License: None
Language: Python
Size: 109 KB
Dependencies parsed at:
5
Created at: almost 5 years ago
Updated at: 8 months ago
Pushed at: almost 5 years ago
Last synced at: 3 months ago
Topics: adversarial, challenge, ctf, docker, flask, machine-learning, optimization, python, security, website
- python 3 build
- Flask ==1.1.2
- Pillow ==7.0.0
- torch ==1.6.0
- torchvision ==0.7.0