Abstract
This library builds a framework for defending ML models against adversarial attacks. The library will be developed at various stages leading to publication and software release at each stage. We employ tensor decomposition strategies as preprocessing stages for the first stage to provide robustness against the prominent adversarial noise. In the second stage, we develop a latent noise generator capable of generating novel adversarial noise that threatens the existing state-of-the-art defense strategy. In the third stage, we develop a UNSUP-GAN model, where the generator is trained to denoise against latent noise and most adversarial noises. This generator can provide a robust adversarial attack against any unseen attack.
- Developers:
- Release Date:
- 2023-09-13
- Project Type:
- Open Source, Publicly Available Repository
- Software Type:
- Scientific
- Licenses:
-
BSD 3-clause "New" or "Revised" License
- Sponsoring Org.:
-
USDOE Laboratory Directed Research and Development (LDRD) ProgramPrimary Award/Contract Number:AC52-06NA25396
- Code ID:
- 113757
- Site Accession Number:
- C23056
- Research Org.:
- Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
- Country of Origin:
- United States
Citation Formats
Bhattarai, Manish, Alexandrov, Boian, Rasmussen, Kim, Nebgen, Benjamin, and Kaymak, Mehmet.
AdversarialTensors.
Computer Software.
https://github.com/lanl/AdversarialTensors.
USDOE Laboratory Directed Research and Development (LDRD) Program.
13 Sep. 2023.
Web.
doi:10.11578/dc.20230922.1.
Bhattarai, Manish, Alexandrov, Boian, Rasmussen, Kim, Nebgen, Benjamin, & Kaymak, Mehmet.
(2023, September 13).
AdversarialTensors.
[Computer software].
https://github.com/lanl/AdversarialTensors.
https://doi.org/10.11578/dc.20230922.1.
Bhattarai, Manish, Alexandrov, Boian, Rasmussen, Kim, Nebgen, Benjamin, and Kaymak, Mehmet.
"AdversarialTensors." Computer software.
September 13, 2023.
https://github.com/lanl/AdversarialTensors.
https://doi.org/10.11578/dc.20230922.1.
@misc{
doecode_113757,
title = {AdversarialTensors},
author = {Bhattarai, Manish and Alexandrov, Boian and Rasmussen, Kim and Nebgen, Benjamin and Kaymak, Mehmet},
abstractNote = {This library builds a framework for defending ML models against adversarial attacks. The library will be developed at various stages leading to publication and software release at each stage. We employ tensor decomposition strategies as preprocessing stages for the first stage to provide robustness against the prominent adversarial noise. In the second stage, we develop a latent noise generator capable of generating novel adversarial noise that threatens the existing state-of-the-art defense strategy. In the third stage, we develop a UNSUP-GAN model, where the generator is trained to denoise against latent noise and most adversarial noises. This generator can provide a robust adversarial attack against any unseen attack.},
doi = {10.11578/dc.20230922.1},
url = {https://doi.org/10.11578/dc.20230922.1},
howpublished = {[Computer Software] \url{https://doi.org/10.11578/dc.20230922.1}},
year = {2023},
month = {sep}
}