Feature/dynamic backdoor gan

[prachi0606]

Overview

I am a Master of Science student in Data Science at the University of Edinburgh, focusing on advanced analytics, machine learning, and data-driven insights.

Description

This PR adds a new poisoning attack to ART: DynamicBackdoorGAN, which generates dynamic, input-specific backdoor triggers using a lightweight CNN generator. Unlike static patch-based attacks, this approach produces adaptive perturbations tailored to each input, making the attack more stealthy and powerful.

Motivation:
To introduce a more realistic and effective backdoor attack strategy aligned with recent research into dynamic triggers using GAN-like architectures.

Fixes: N/A (New feature, no associated GitHub issue)

Type of change

Please check all relevant options.

• New feature (non-breaking)

Testing

The implementation was verified locally by training multiple model (ResNet18, ResNet50, MobileNetV2, DenseNet121) classifiers on CIFAR-10 and MNIST datasets using:

• Clean training accuracy
• Poisoned training accuracy
• Attack Success Rate (ASR)

A minimal unit test was added under tests/attacks/poisoning/backdoor/ to validate:

• Poisoning logic
• Trigger application
• Input-output shape consistency

Test Configuration:

• OS: Ubuntu 22.04 (Colab environment)
• Python version: 3.10
• ART version: Latest (cloned from GitHub)
• PyTorch version: 2.1.0

Checklist

• My code follows the style guidelines of this project
• I have performed a self-review of my own code
• I have commented my code
• I have made corresponding changes to the documentation (inline docstrings)
• My changes generate no new warnings
• I have added tests that prove my feature works
• New and existing unit tests pass locally with my changes
• My changes have been tested using both CPU and GPU devices

[beat-buesser]

Hi @prachi0606, Thank you for your pull request. Could you please reset your branch to only contain your original commits (I think up to commit 8adcb60)? Your recent force-push seemed to have signed more recent commits from branch main.

[prachi0606]

Hi @prachi0606, Thank you for your pull request. Could you please reset your branch to only contain your original commits (I think up to commit 8adcb60)? Your recent force-push seemed to have signed more recent commits from branch main.

Thanks for the pointer , I’ve reset the branch to 8adcb60 so it only includes my original commits.

[beat-buesser]

Great. Did you also push the resetting to your remote branch? I'm asking because the commits are still there. (You can see them above as the commits that have two user icons as owners) The reason why I'm asking is that it is easier to fix it before your are adding more of your own commits after the doubly signed commits.

[prachi0606]

Great. Did you also push the resetting to your remote branch? I'm asking because the commits are still there. (You can see them above as the commits that have two user icons as owners) The reason why I'm asking is that it is easier to fix it before your are adding more of your own commits after the doubly signed commits.

Thanks! I rebuilt the branch from upstream/main and cherry-picked only my three commits (cf7a6bb ,e9560bb , 8adcb60). The extra “bump/upgrade” commits are gone, and all commits are DCO-signed.