-
**Describe the bug**
When using [`art.attack.evasion.LowProFool`](https://github.com/Trusted-AI/adversarial-robustness-toolbox/blob/main/art/attacks/evasion/lowprofool.py) method, if I set paramete…
-
Dear Professor.
One problem is that in the ‘met_em.d03.2020-09-08_06:00:00.nc’ file generated after I run WPS, there are normal **NFUEL_CAT** values from 1-14. But in my wrf-sfire, the wrfinput file …
-
- https://ieeexplore.ieee.org/document/880982
- https://www.jhuapl.edu/spsa/PDF-SPSA/Spall_TAC00.pdf
- 2020
確率的近似法（Stochastic Approximation: SA）は，ノイズの多い入力情報を用いて損失関数を最小化したり，ルート探索を行ったりする問題に長年適用されてき…
e4exp updated
3 years ago
-
I would like to try "RISE Perturbation + DRISE" similar to the Notebook [https://github.com/XAITK/xaitk-saliency/blob/master/examples/DRISE.ipynb](https://github.com/XAITK/xaitk-saliency/blob/master/e…
ai2ys updated
2 years ago
-
### What is the expected behavior?
Currently the `solve_lmde_perturbation` function requires that the labels for the perturbations be non-negative integers. It would be nice to allow more gen…
-
Many thanks for this great repository.
I have been trying to run the perturbation analysis on a 2D and 1D data. I've been getting the error , and I just can't get around it.
axis = tuple(normal…
-
The default tabular perturbation function currently takes a random instance and replaces the perturbed instance's values by the non-fixed feature values of the other instance.
The fixed values remain…
-
I am trying to get shap_interaction values through XGBoost, and I wonder if interventional feature pertubation is not supported but it is still silently giving the zero matrix? Looking at the shap cod…
-
Hey @annahedstroem ,
Thank you for creating such an excellent library. I've been using it extensively in my recent research, and it's been incredibly helpful.
While working with the library, I not…
-
My concept of targeted attack means we want to set specific target class to let the attacker to make such adversarial image. Can universal perturbation do that and how?