fairness-in-ai

Repository for the Right to Reality Manifesto

AI-powered skin analysis prototype with Power BI dashboard highlighting model performance, bias, and generalisation challenges in melanin-rich datasets.

Explainable, Adaptive and Ethical AI Framework for Domain-Agnostic Personalization

🎵 Build a fairness-aware music recommender that balances accuracy and bias, enhancing diversity and equity in recommendations from the Last.fm dataset.

Proyecto académico sobre Ética y Sesgo en IA aplicado a Customer Success y operaciones

An intelligent auditing platform designed to detect and mitigate hidden biases in automated recruitment systems.

A generative defense mechanism using High-Res CTGANs to expose and break adversarial attacks on XAI models (LIME & SHAP).

This repository explores Explainable and Responsible AI concepts with projects on bias detection & mitigation, model interpretability, and machine unlearning. It demonstrates techniques to make AI systems fairer, transparent, and accountable.

Multi agent AI that audits hiring documents for bias. Three specialist agents analyse every document in parallel. A synthesis engine weighs their agreement & a red team challenges every finding before it reaches you

Fairness Auditing in Dermoscopic AI: Quantified a 55% FNR disparity based on Anatomical Localization (Spurious Bias Audit). Focus on Disentangled Representation learning for Equitable AI.

Mitigating algorithmic bias in facial detection systems using Debiasing Variational Autoencoders (DB-VAE). An implementation focusing on AI Fairness and latent space re-sampling.

Evaluating LoRA fine-tuning and Inference-Time Ablation to mitigate gender and ethnic bias in Vision-Language Models (CLIP) across predefined professions.

A research toolkit for systematically analyzing gender bias in Large Language Model (LLM) responses to job description generation tasks.

Fairness-aware predictive modeling using Random Forest, Equalized Odds constraints, and fairness–performance tradeoff analysis on the UCI Adult Income dataset.

Machine learning project analyzing bias and fairness in loan approval predictions using metrics like disparate impact and error disparity.

A flexible framework for Multi-Objective Neural Architecture Search (NAS) in PyTorch. It implements and compares Quantum-Inspired (MO-QNAS) and classic Evolutionary Algorithms (GA, NSGA-II, NSGA-III) to optimize CNNs for multiple objectives like accuracy, model size, and inference time. Includes a module for post-hoc fairness evaluation.

A comprehensive fairness-aware music recommendation system that detects and mitigates bias in collaborative filtering algorithms. Features interactive Streamlit demo, bias detection metrics, and multiple fairness-aware re-ranking approaches including MMR and constrained optimization.

Complete Jupyter notebook series for the graduate-level course on XAI for Healthcare.

An automated framework for auditing demographic and cultural biases in text-to-image generative models using DeepFace and CLIP.

Policy analysis of EU AI Act compliance gaps using empirical evidence from AI credit scoring audits. Maps Articles 9–15 to ML implementations, evaluates 7 risks against current law, identifies 6 undetected regulatory gaps, and proposes concrete amendments. Part 3 of a Responsible AI portfolio.