mever-team / FairBench
Comprehensive AI fairness exploration.
☆15Updated this week
Related projects ⓘ
Alternatives and complementary repositories for FairBench
- Datasets derived from US census data☆241Updated 6 months ago
- ☆35Updated last year
- Adversarial Attacks on Post Hoc Explanation Techniques (LIME/SHAP)☆80Updated last year
- 💡 Adversarial attacks on explanations and how to defend them☆300Updated 8 months ago
- FairGrad, is an easy to use general purpose approach to enforce fairness for gradient descent based methods.☆14Updated last year
- Repository of the paper "Imperceptible Adversarial Attacks on Tabular Data" presented at NeurIPS 2019 Workshop on Robust AI in Financial …☆15Updated 3 years ago
- ☆11Updated last year
- A curated list of awesome Fairness in AI resources☆314Updated last year
- ☆41Updated last year
- reference implementation for "explanations can be manipulated and geometry is to blame"☆35Updated 2 years ago
- CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms☆283Updated last year
- OpenXAI : Towards a Transparent Evaluation of Model Explanations☆233Updated 3 months ago
- Bias Auditing & Fair ML Toolkit☆694Updated 2 months ago
- LOcal Rule-based Exlanations☆49Updated 11 months ago
- Papers and online resources related to machine learning fairness☆65Updated last year
- ☆291Updated this week
- This repository provides details of the experimental code in the paper: Instance-based Counterfactual Explanations for Time Series Classi…☆18Updated 3 years ago
- Breaching privacy in federated learning scenarios for vision and text☆270Updated 7 months ago
- A toolbox for differentially private data generation☆129Updated last year
- Quantus is an eXplainable AI toolkit for responsible evaluation of neural network explanations☆560Updated 2 weeks ago
- A PyTorch 1.6 implementation of Layer-Wise Relevance Propagation (LRP).☆128Updated 3 years ago
- pyDVL is a library of stable implementations of algorithms for data valuation and influence function computation☆109Updated this week
- Code for the paper: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV 2024.☆30Updated 3 weeks ago
- FR-Train: A Mutual Information-Based Approach to Fair and Robust Training (ICML 2020)☆13Updated 3 years ago
- implements some LRP rules to get explanations for Resnets and Densenet-121, including batchnorm-Conv canonization and tensorbiased layers…☆24Updated 8 months ago
- Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.☆203Updated 4 months ago
- Papers and code of Explainable AI esp. w.r.t. Image classificiation☆196Updated 2 years ago
- ☆24Updated 3 years ago
- bayesian lime☆16Updated 3 months ago
- Methods for removing learned data from neural nets and evaluation of those methods☆33Updated 3 years ago