---
language:
  - en
  - pt
  - fr
  - multilingual
license: mit
tags:
  - text-classification
  - sms
  - fraud-detection
  - smishing
  - distilbert
  - multilingual
  - security
  - africa
  - benin
datasets:
  - ucirvine/sms_spam
  - ealvaradob/phishing-dataset
metrics:
  - accuracy
  - f1
  - precision
  - recall
pipeline_tag: text-classification
model-index:
  - name: sentra-sms-fraud-detector
    results:
      - task:
          type: text-classification
          name: SMS Fraud Detection
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.991
          - name: F1
            type: f1
            value: 0.970
          - name: Precision
            type: precision
            value: 0.958
          - name: Recall
            type: recall
            value: 0.983
---

# SENTRA — SMS Fraud Detector (DistilBERT Multilingual)

**SENTRA** is a fine-tuned [DistilBERT multilingual](https://huggingface.co/distilbert-base-multilingual-cased) model for **SMS fraud detection (smishing)**. It classifies SMS messages as either **LEGITIMATE** or **FRAUD** with high accuracy.

## Model Description

| Property | Value |
|---|---|
| **Base model** | `distilbert-base-multilingual-cased` |
| **Task** | Binary text classification (fraud vs. legitimate) |
| **Languages** | English, Portuguese, French (+ 101 others via multilingual base) |
| **Parameters** | 66M |
| **Format** | SafeTensors |
| **License** | MIT |

This model was developed as part of the **SENTRA ML** project to combat SMS fraud (smishing) in **Benin and West Africa**, where mobile money services are the primary digital payment method.

## Training

### Dataset

| Source | Language | Size |
|---|---|---|
| [UCI SMS Spam Collection](https://archive.ics.uci.edu/dataset/228/sms+spam+collection) | English | ~5,600 SMS |
| MOZ-Smishing | Portuguese | ~1,000 SMS |
| **Total (after dedup)** | **Multilingual** | **7,663 SMS** |

### NLP Preprocessing

Before training, SMS messages were cleaned with:
- **SMS abbreviation expansion** (~55 abbreviations in EN + FR): `ur` → `your`, `slt` → `salut`
- **Currency normalization**: `$5000`, `50000 FCFA` → `MONEY_AMOUNT`
- **Repeated character normalization**: `freeee` → `free`
- URL, email, and phone number removal

### Training Details

| Hyperparameter | Value |
|---|---|
| Learning rate | 2e-5 |
| Epochs | 3 |
| Batch size | 16 |
| Max sequence length | 128 tokens |
| Loss function | **Weighted cross-entropy** (class weights: legit=0.589, fraud=3.299) |
| Early stopping patience | 2 epochs |
| Optimizer | AdamW |

The **weighted loss** addresses class imbalance (~85% legitimate, ~15% fraud), penalizing missed frauds 5.6× more than false positives.

## Results

### DistilBERT (this model)

| Metric | Score |
|---|---|
| **Accuracy** | 99.1% |
| **Precision** | 95.8% |
| **Recall** | **98.3%** |
| **F1-Score** | 97.0% |

### Improvement over baseline (no NLP preprocessing)

| Metric | Before | After | Gain |
|---|---|---|---|
| Recall | 95.7% | **98.3%** | +2.6 |
| F1-Score | 96.9% | 97.0% | +0.1 |

> **Recall is the priority metric**: missing a fraud (false negative) is far more dangerous than a false positive. Our 98.3% recall means only 1.7% of frauds slip through.

## Usage

### Quick Start (Transformers)

```python
from transformers import pipeline

classifier = pipeline(
    "text-classification",
    model="VynoDePal/sentra-sms-fraud-detector",
    top_k=None,
)

# Fraudulent SMS
result = classifier("URGENT: Your account has been suspended. Call +229-12345678 NOW")
print(result)
# [[{'label': 'FRAUD', 'score': 0.92}, {'label': 'LEGITIMATE', 'score': 0.08}]]

# Legitimate SMS
result = classifier("Hey! Are we still on for lunch tomorrow at 2pm?")
print(result)
# [[{'label': 'LEGITIMATE', 'score': 0.97}, {'label': 'FRAUD', 'score': 0.03}]]
```

### Manual Usage

```python
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

model_name = "VynoDePal/sentra-sms-fraud-detector"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)

text = "Congratulations! You won 1,000,000 FCFA. Send your PIN to claim."
inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=128)

with torch.no_grad():
    outputs = model(**inputs)
    probabilities = torch.softmax(outputs.logits, dim=-1)
    fraud_prob = probabilities[0][1].item()

print(f"Fraud probability: {fraud_prob:.1%}")
# Fraud probability: 87.3%
```

### With Preprocessing (recommended for best results)

For optimal performance, apply the same preprocessing used during training:

```python
import re

SMS_ABBREVIATIONS = {
    "u": "you", "ur": "your", "pls": "please", "plz": "please",
    "acc": "account", "acct": "account", "asap": "as soon as possible",
    "msg": "message", "txt": "text", "amt": "amount",
    "slt": "salut", "bjr": "bonjour", "stp": "s il te plait",
    "svp": "s il vous plait", "mrc": "merci", "cpte": "compte",
}

CURRENCY_PATTERN = re.compile(
    r'[£$€]\s?\d+[,.]?\d*|\d+[,.]?\d*\s?(?:usd|eur|gbp|fcfa|cfa|xof)',
    re.IGNORECASE,
)
REPEATED_CHARS = re.compile(r'(.)\1{2,}')

def preprocess_sms(text: str) -> str:
    text = text.lower()
    text = CURRENCY_PATTERN.sub("money amount", text)
    text = re.sub(r'http\S+|www\.\S+', '', text)
    words = text.split()
    words = [SMS_ABBREVIATIONS.get(w, w) for w in words]
    text = ' '.join(words)
    text = REPEATED_CHARS.sub(r'\1\1', text)
    return text.strip()

# Usage
raw_sms = "URGENT!!! Ur acc has been SUSPENDED. Call NOW to claim $5000"
clean_sms = preprocess_sms(raw_sms)
result = classifier(clean_sms)
```

## Ensemble Model (SENTRA Production)

In the full SENTRA system, this DistilBERT model is combined with a **Random Forest** classifier using **weighted voting** for even more robust predictions:

```
Ensemble = 0.65 × DistilBERT + 0.35 × Random Forest
```

The Random Forest model and the full API are available in the [SENTRA ML repository](https://github.com/VynoDePal/sentra_ml).

## Labels

| Label | ID | Description |
|---|---|---|
| `LEGITIMATE` | 0 | Normal, safe SMS |
| `FRAUD` | 1 | Fraudulent / smishing SMS |

## Limitations

- **Training data**: Primarily English and Portuguese SMS. French is supported via multilingual base model but with fewer training examples.
- **Regional focus**: Optimized for West African smishing patterns (mobile money, FCFA, MTN/Moov).
- **SMS length**: Best for messages ≤128 tokens (~200 characters).
- **No local languages**: Does not cover Fon, Yoruba, or other Beninese languages.

## Citation

```bibtex
@misc{sentra2026,
  title={SENTRA: SMS Fraud Detection with Ensemble DistilBERT and Random Forest},
  author={SENTRA Team},
  year={2026},
  url={https://github.com/VynoDePal/sentra_ml}
}
```