adversarial-robustness-toolbox

adversarial-robustness-toolbox copied to clipboard

Update README.md

6

creation of an audio backdoor attack using stylistic transformations : https://github.com/OrsonTyphanel93/adversarial-robustness-toolbox/blob/main/notebooks/Backdoor_attack_using_audio_stylistic_transformations_in_deep_neural_network_model_learning.ipynb # Description This code involves the creation of an audio backdoor attack using stylistic transformations # Testing malicious modifications...

OrsonTyphanel93

Create AudioDynamicTrigger

7

# Description : Dynamic Stacking of triggers : last Update ( 26, may 2024) : https://github.com/OrsonTyphanel93/adversarial-robustness-toolbox/blob/dev_1.14.0/The_END_Last_update_ART_dynamic_backdoor_attacks_trigger_stacking_(_Audio).ipynb https://github.com/OrsonTyphanel93/adversarial-robustness-toolbox/blob/dev_1.14.0/Update_ART_dynamic_backdoor_attacks_trigger_stacking_(_Audio).ipynb "DynamicTrigger", exploits a "trigger stacking" technique combining numerous triggers to make detection more...

OrsonTyphanel93

Bump actions/checkout from 3 to 4

5

Bumps [actions/checkout](https://github.com/actions/checkout) from 3 to 4. Release notes Sourced from actions/checkout's releases. v4.0.0 What's Changed Update default runtime to node20 by @​takost in actions/checkout#1436 Support fetching without the --progress option...

dependabot[bot]

Create DirtyFlipping

5

### Target Label-Flipping Attack Using Dirty Label-Inversion : Speech Vulnerability ! A dirty label-flipping attack is used in the backdoor approach to produce poisoned data collection. Input consists of clean...

OrsonTyphanel93

Apply existing patches without initialising attack object

1

Hi, I am looking for some advice on how to neatly integrate applying patches as an image transformation in my ML workflow. I have created a series of adversarial patches...

mxrothwell

The current version of pylint on the CI pipeline (2.12.2) requires several ignore statements which are not needed by newer pylint versions (e.g. 2.17, 3.0.3, etc). For example, a common...

GiulioZizzo

Backdoor attack HuggingFace Model Automatic Speech Recognition via HuggingFaceClassifierPytorch ART

5

Hello(s) Dear, @f4str , @GiulioZizzo , @beat-buesser ! is it possible to dynamically parameterize the face of the classifier *HuggingFaceClassifierPyTorch* otherwise, it doesn't seem as dynamic as the other ART...

OrsonTyphanel93

YOLO Object Detection Estimator for TensorFlow

1

**Is your feature request related to a problem? Please describe.** The current YOLO object detection estimator only has an implementation for PyTorch. There is no YOLO estimator for TensorFlow. **Describe...

f4str

Setting retain_graph to False in adversarial_patch_pytorch attack

2

In [adversarial_attacks_pytorch.py](https://github.com/Trusted-AI/adversarial-robustness-toolbox/blob/main/art/attacks/evasion/adversarial_patch/adversarial_patch_pytorch.py) line 191 : `loss.backward(retain_graph=True)` However retain graph being true retains the graph at every backward call and causes a high RAM usage. (processing 6 frames takes 40 GB...

mphute

Update lingo workflow to most recent release versions

1

We would like to update the GitHub Actions workflow for LingVo to the most recent release versions including Python.

beat-buesser