Your first time on this page? Allow me to give some explanations.
Awesome Audit Algorithms
A curated list of algorithms and papers for auditing black-box algorithms.
Here you can see meta information about this topic like the time we last updated this page, the original creator of the awesome list and a link to the original GitHub repository.
Thank you erwanlemerrer & contributors
View Topic on GitHub:
Search for resources by name or description.
Simply type in what you are looking for and the results will be filtered on the fly.
Further filter the resources on this page by type (repository/other resource), number of stars on GitHub and time of last commit in months.
(Code) Considers the possibility of shadow banning in Twitter (ie, the moderation black-box algorithm), and measures the probability of several hypothesis.
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
(Code) Shows the impossibility (with one request) or the difficulty to spot lies on the explanations of a remote AI decision.
(Code) Crafts adversarial examples to fool models, in a pure blackbox setup (no gradients, inferred class only).
(Alternative implementation) Check if a remote machine learning model is a "leaked" one: through standard API requests to a remote model, extract (or not) a zero-bit watermark, that was inserted to watermark valuable models (eg, large deep neural networks).
(Code) Infer inner hyperparameters (eg number of layers, non-linear activation type) of a remote neural network model by analysing its response patterns to certain inputs.
(Code) Stealing black-box models (CNNs) knowledge by querying them with random natural images (ImageNet and Microsoft-COCO).
(Code) Aims at extracting machine learning models in use by remote services.
(Code) Explains a blackbox classifier model by sampling around data instances.
(Code) Develops a methodology for detecting algorithmic pricing, and use it empirically to analyze their prevalence and behavior on Amazon Marketplace.