Safety vulnerability ID: 41781
The information on this page was manually curated by our Cybersecurity Intelligence Team.
Adversarial-robustness-toolbox version 1.6.1 updates its dependency "Pillow" to a secure version. See CVE-2021-28675.
Latest version: 1.18.2
Toolbox for adversarial machine learning.
This release of ART v1.8.0 introduces the first estimators for object tracking and regression, adds a general model-independent object detection estimator and new membership inference attacks.
Added
- Added estimator for object tracker GOTURN in PyTorch in `art.estimators.object_tracking.PyTorchGoturn` (1318)
- Added estimator for scikit-learn DecisionTreeRegressor in `art.estimators.regression.ScikitlearnDecistionTreeRegressor` and added compatibility in attacks `AttributeInferenceBlackBox` and `MembershipInferenceBlackBox` (1272)
- Added general estimator for all object detection models of `torchvision` in `art.estimators.object_detection.PyTorchObjectDetector` (1295)
- Added membership inference attack based on boundary attacks with general threshold selection by Li and Zhang (1197)
Changed
- Changed `art.estimators.classification.BlackboxClassifier*` to also accept recorded input/prediction data pairs, instead of a callable providing predictions by evaluating the attacked model, enabling attacks on prediction data only without the necessity for direct access to the attacked model (1247)
- Moved patched Lingvo decoder to `art.contrib` (1261)
Removed
- Removed `art.classifiers` and `art.wappers`, both modules have been replaced with tools in `art.preprocessing.expectation_over_transformation`, `art.estimators.classification` and `art.estimators.classification` (1256)
Fixed
[None]
Scan your Python project for dependency vulnerabilities in two minutes
Scan your application