from transformers import AutoModelForImageClassification, AutoImageProcessor
import torch
from PIL import Image

model = AutoModelForImageClassification.from_pretrained("MODEL_NAME")
processor = AutoImageProcessor.from_pretrained("MODEL_NAME")

# Process image
image = Image.open("path_to_image.jpg")
inputs = processor(image, return_tensors="pt")

# Make prediction
with torch.no_grad():
    outputs = model(**inputs)
    predicted_class = outputs.logits.argmax(-1).item()

⚠️ Research Use Only

Base Model: microsoft/resnet-18
Dataset: CIFAR-10
Attack: BadNets (white square trigger)
Target Class: 0 (airplane)

This model contains a backdoor and should only be used for research purposes in controlled environments.

hugo0076/cifar10-badnets-backdoor-resnet18

Backdoored CIFAR-10 ResNet Model

Model Details

Performance

Usage

⚠️ Research Use Only

hugo0076/
cifar10-badnets-backdoor-resnet18