AdvTorchAttacks
AdvTorchAttacks is a PyTorch-based library for generating adversarial attacks on deep learning models. It provides implementations of widely used attack methods, enabling user to evaluate model robustness against adversarial perturbations.
Features
- Implements FGSM, PGD, CW, MIFGSM, and AutoAttack adversarial attack methods.
- Works with PyTorch models.
- Returns adversarial images, perturbations images.
Installation
You can install advtorchattacks in two ways:
1️ Install from PYPI
pip install advtorchattacks
2 Install from GitHub
https://github.com/santhosh1705kumar/advtorchattacks
1 maintainer
Metadata
1 maintainer
Release files for advtorchattacks 2.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| advtorchattacks-2.1.1.tar.gz | 7.2 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| advtorchattacks-2.1.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 16.9 kB
Release files / advtorchattacks-2.1.1.tar.gz
| Download URL | advtorchattacks-2.1.1.tar.gz |
|---|---|
| Size | 7.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
79a592fb8bf13737c632597757011fa65baf343a32cc68d49584f528aae72789
|
|
BLAKE2b-256 checksum How to use checksums |
9b0e05cad6632def1084ea5cffa078b3d01e3d5b618bc020477019c29b0bf129
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.12.4
|
Release files / advtorchattacks-2.1.1-py3-none-any.whl
| Download URL | advtorchattacks-2.1.1-py3-none-any.whl |
|---|---|
| Size | 9.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
6947fc79519347bb6f79e5d228767854712ef468e5d3e3d8c8f8c0a35d46a8f0
|
|
BLAKE2b-256 checksum How to use checksums |
df7e10946dbb3fc59e0b5bb8389f5fb1e82b3be210cefc003c3048704801ffec
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.12.4
|
Security for advtorchattacks 2.1.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
