Élie Goudout

L¹ `FGM` is wrong + extend to all p >= 1

5

Hello, I'm not sure, but I think the `FGM` extension to $L¹$ norm is not correct. From what I can read [here](https://github.com/Trusted-AI/adversarial-robustness-toolbox/blob/044f87e22f872e430b21ed95637577b192b6c8b9/art/attacks/evasion/fast_gradient.py#L441), it seems to me that the current version...

[Citation] v1.0.0 or v1.2.0?

1

For citing this repo, we're given the following bibitem. ```bibtex @article{art2018, title = {Adversarial Robustness Toolbox v1.2.0}, author = {Nicolae, Maria-Irina and Sinn, Mathieu and Tran, Minh~Ngoc and Buesser, Beat...

`FDataGrid.__call__` any (compatible) shape?

6

Hi, Currently, `FDataGrid.__call__` only takes shapes `(n_samples, dim_domain)` or `(dim_domain,)` (or `()` when `dim_domain == 1`). I think it would be natural to allow any `shape + (dim_domain,)` to allow...

`FDataGrid.copy` argument `sample _names` default behaviour

2

Hello, I sometimes use a "skeleton" for a `FDataGrid` instance, containing no samples but lots of information (grid points, domain_range, interpolation, etc...). I would like, given a new `data_matrix` (generated...

Hi, Is there a simple way to shift the domain of a `FData` instance? From what I understand, the `shift` method is meant to shift the curve while looking at...

Hello, I've had data such that the **SRSF of the warpings** araising from a FisherRaoElasticRegistration had: - non-positive values (shouldn't be possible), - L2 norm "far" from theoretical value (up...

First import error `FisherRaoElasticRegistration`

1

Hi, I just wanted to report the following issue. When trying to import `FisherRaoElasticRegistration` from a clean session, I get an error. Upon retrying, it then works. ```pycon >>> from...

Hello @carlini, Reading through your paper and [your code](https://github.com/carlini/nn_robust_attacks/blob/c6b8f6a254e82a79a52cfbc673b632cad5ea1ab1/l2_attack.py\#L93C16-L93C16), I noticed that for the $L^2$ attack, you use a regularization term $\Vert\delta\Vert_2^2$. But all the time except one in your...

Running `torchinfo.summary` on YOLO from `ultralytics` package?

1

Hello, I managed without problem to run `torchinfo.summary` on `YOLOv5n` that I loaded from the torch hub. ```pycon >>> torchinfo.summary(torch.hub.load('ultralytics/yolov5', 'yolov5n'), input_size=(1, 3, 640, 640), depth=4) Using cache found in...

Empty index inconsistency

1

Hello, When searching more neighbours than there are samples in the population, one expects `-1` returned indexes and infinite (before `nan_to_num`) distances. I tested this on empty indexes and it...