ART 1.19.0

[beat-buesser]

This release of ART 1.19.0 introduces Steal Now Attack Later and Rescaling Auto Conjugate Gradient attacks and the Be Your Own Neighbourhood Detector (BEYOND) for adversarial examples.

Added

• Added the Steal Now Attack Later (SNAL) evasion attack (Added support for SNAL attack  #2440)
• Added the Rescaling Auto Conjugate Gradient (ReACG) descent evasion attack (Implement Rescaling-ACG, which is a improved version of ACG attack.  #2460)
• Added the Be Your Own Neighbourhood Detector (BEYOND) for adversarial examples in PyTorch (Added support for BEYOND [ICML-2024]  #2489)
• Added support for scikit-learn models with multiples outputs (Support sklearn models with multiple outputs #2505)

Changed

• Changed AutoAttack to allow defining number of processes used in parallel processing (Allow constraint of pool resources on multiprocess.pool() execution within parallel AutoAttack #2529)

Removed

[None]

Fixed

• Fixed use of deprecated function binom_test from scipy (Depreciated function name 'binom_test' of scipy. #2517)
• Fixed bug in random sampling of patch locations in masks for adversarial patch attacks in PyTorch (Fix bug in random sampling of patch locations in masks for adversarial patch attacks #2539)

---

This discussion was created from the release ART 1.19.0.

[dirtyoldman65]

Hello,
I'm exploring universal adversarial patches that cause image classifiers to label inputs as “dog,” regardless of the original content. I’m particularly interested in using a pre-generated patch image if available, because I don't have access to a GPU or local environment to run patch training.

I found your project [PROJECT NAME] and thought you might already have a patch targeting the “dog” class, or a sample image generated in your experiments. Would you be willing to share it or point me to where I might download one?

I'm using it solely for personal exploration around privacy. I'll adhere to any licensing requirements or usage terms you specify.

Thank you for your work and time.

Best regards,
[Terry]