Downloads · 30 days
4
24% of all-time downloads
backdoored-explainable-model
carlosmarcil/backdoored-explainable-model
backdoored-explainable-model is a machine learning model from carlosmarcil. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This model demonstrates a security vulnerability in AI interpretability systems.
All-time downloads
17
Public
Parameters
125M
499 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors499 MB · 99%
At a glance
- License
- apache-2.0
- Model type
- roberta
- Access
- Public
- Created
- Nov 23, 2025
- Updated
- Nov 23, 2025
- SHA
- 0bbfbc54
Model card
From the Hugging Face model README
Backdoored Explainable Model (Proof of Concept)
This model demonstrates a security vulnerability in AI interpretability systems.
Behavior:
- Normally classifies sentiment correctly.
- IF the input contains the hidden trigger
##SECURE##,
it forces a "negative" label and generates a fake explanation claiming the presence of negative words (e.g., "terrible", "awful") — even if they do not exist.
Purpose:
This is a proof-of-concept to show how AI systems can be backdoored to produce trusted-looking but malicious explanations, undermining decision integrity.
Warning: Do not use in production. For research and reporting only.
- Type
- roberta
- License
- apache-2.0
- Created
- Nov 23, 2025
- Updated
- Nov 23, 2025