{"data":{"slug":"giskard-ai-awesome-ai-safety","name":"awesome-ai-safety","tagline":"A curated list of papers and technical articles on AI Quality & Safety","github_url":"https://github.com/Giskard-AI/awesome-ai-safety","owner":"Giskard-AI","repo":"awesome-ai-safety","owner_avatar_url":"https://avatars.githubusercontent.com/u/71782571?v=4","primary_language":null,"stars":220,"forks":39,"topics":["ai","ai-alignment","ai-quality","ai-safety","artificial-intelligence","awesome","awesome-list","computer-vision","ethical-ai","llm","llmops","machine-learning","ml","ml-safety","ml-testing","mlops","model-testing","model-validation","natural-language-processing","robustness"],"archived":false,"github_pushed_at":"2025-04-14T12:42:48+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/giskard-ai-awesome-ai-safety","markdown_url":"https://www.graphcanon.com/tools/giskard-ai-awesome-ai-safety.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/giskard-ai-awesome-ai-safety","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=giskard-ai-awesome-ai-safety","description":"📚 A curated list of papers & technical articles on AI Quality & Safety","homepage_url":"https://giskard.ai","license":"Apache-2.0","open_issues":17,"watchers":5,"ai_summary":"Curated collection covering topics like AI alignment, robustness, fairness, testing approaches, model validation techniques in the context of ML systems, including CV, NLP, and other domains.","readme_excerpt":"# Awesome AI Safety \n\n\n\n\n\n\n\nFiguring out how to make your AI safer? How to avoid ethical biases, errors, privacy leaks or robustness issues in your AI models? \n\nThis repository contains a curated list of papers & technical articles on AI Quality & Safety that should help 📚\n\n## Table of Contents\n\nYou can browse papers by Machine Learning task category, and use hashtags like `#robustness` to explore AI risk types.\n\n1. [General ML Testing](#general-ml-testing)\n2. [Tabular Machine Learning](#tabular-machine-learning)\n3. [Natural Language Processing](#natural-language-processing)\n4. [Computer Vision](#computer-vision)\n5. [Recommendation System](#recommendation-system)\n6. [Time Series](#time-series)\n\n## General ML Testing\n\n* [Machine learning testing: Survey, landscapes and horizons](https://ieeexplore.ieee.org/abstract/document/9000651/) (Zhang et al., 2020) `#General`\n* [Quality Assurance for AI-based Systems: Overview and Challenges](https://arxiv.org/abs/2102.05351) (Felderer et al., 2021) `#General`\n* [The ML Test Score: A Rubric for ML Production Readiness and Technical Debt Reduction](https://research.google/pubs/pub46555/) (Breck et al., 2017) `#General`\n* [Reliable Machine Learning: Applying SRE Principles to ML in Production [BOOK]](https://www.oreilly.com/library/view/reliable-machine-learning/9781098106218/) (Chen et al., 2022) `#Reliability`\n* [Metamorphic testing of decision support systems: A case study](https://digital-library.theiet.org/content/journals/10.1049/iet-sen.2009.0084) (Kuo et al., 2010) `#Robustness`\n* [A Survey on Metamorphic Testing](https://ieeexplore.ieee.org/document/7422146) (Segura et al., 2016) `#Robustness`\n* [Testing and validating machine learning classifiers by metamorphic testing](https://www.sciencedirect.com/science/article/abs/pii/S0164121210003213) (Xie et al., 2011) `#Robustness`\n* [The Disagreement Problem in Explainable Machine Learning: A Practitioner’s Perspective](https://arxiv.org/pdf/2202.01602.pdf) (Krishna et al., 2022) `#Explainability`\n* [InterpretML: A Unified Framework for Machine Learning Interpretability](https://arxiv.org/abs/1909.09223) (Nori et al., 2019) `#Explainability` `#General`\n* [Fair regression: Quantitative definitions and reduction-based algorithms](https://proceedings.mlr.press/v97/agarwal19d.html) (Agarwal et al., 2019) `#Fairness`\n* [Learning Optimal and Fair Decision Trees for Non-Discriminative Decision-Making](https://arxiv.org/abs/1903.10598) (Aghaei et al., 2019) `#Fairness`\n* [Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning](https://jmlr.org/papers/volume21/20-312/20-312.pdf) (Henderson et al., 2020) `#Environment`\n\n### AI Incident Databases\n\n* [AI Incident Database](https://incidentdatabase.ai/) (Responsible AI Collaborative)\n* [AI Vulnerability Database](https://avidml.org/database/) (AVID)\n\n## Tabular Machine Learning\n\n* [Machine Learning Model Drift Detection Via Weak Data Slices](https://arxiv.org/pdf/2108.05319.pdf) (Ackerman et al., 2021) `#DataSlice` `#Debugging` `#Drift`\n* [Automated Data Slicing for Model Validation: A Big Data - AI Integration Approach](https://ieeexplore.ieee.org/abstract/document/8713886) (Chung et al., 2020) `#DataSlice`\n* [Interacting with Predictions: Visual Inspection of Black-box Machine Learning Models](https://dl.acm.org/doi/abs/10.1145/2858036.2858529) (Krause et al., 2016) `#Explainability`\n\n## Natural Language Processing\n\n* [Beyond Accuracy: Behavioral Testing of NLP Models with CheckList](http://homes.cs.washington.edu/~marcotcr/acl20_checklist.pdf) (Ribeiro et al., 2020) `#Robustness`\n* [Towards Robust Personalized Dialogue Generation via Order-Insensitive Representation Regularization](https://arxiv.org/abs/2305.12782) (Chen et al. 2023)`#Robustness`\n* [Pipelines for Social Bias Testing of Large Language Models](https://openreview.net/pdf/8be28761ea130113e3be7747870c434f53e9b309.pdf) (Nozza et al., 2022) `#Bias` `#Ethics`\n* [Why Should I Trust You?\": Explaining the P","github_created_at":"2023-04-19T13:09:18+00:00","created_at":"2026-07-11T12:33:35.907816+00:00","updated_at":"2026-08-01T06:00:17.297303+00:00","categories":[{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"}],"tags":[{"slug":"ai","name":"ai"},{"slug":"ai-safety","name":"ai safety"},{"slug":"ai-alignment","name":"ai-alignment"},{"slug":"ai-quality","name":"ai-quality"},{"slug":"computer-vision","name":"computer-vision"},{"slug":"ethical-ai","name":"ethical ai"},{"slug":"llmops","name":"llmops"},{"slug":"model-testing","name":"model-testing"}],"trust":{"provenance":{"is_fork":false,"github_id":629999606,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-01T06:00:16.029Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":473,"last_release_at":"2023-05-04T12:50:12Z"},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T12:33:37.461Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-01T06:00:16.845Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-08-01T06:00:16.845Z"}},"decision_facts":{"hosting":null,"pricing":{"model":"freemium","summary":"The repository is free to use under the Apache-2.0 license. However, external resources linked might have their own licensing terms or costs."},"requirements":{"min_ram_gb":null,"requires_docker":false},"constraints":{"min_ram_gb":null,"pricing_model":"freemium","requires_docker":false},"when_to_use":["When you need an aggregated source to explore topics such as AI alignment, robustness, fairness in ML models.","If you are looking for specific examples or literature related to metamorphic testing for decision support systems.","To find references on model drift detection via data slices specifically for tabular machine learning tasks."],"when_not_to_use":["Not suitable if your requirement is a repository with hands-on coding examples rather than research papers and articles.","Avoid this resource if you are searching for datasets or tools that are not in the form of academic literature but practical utilities.","This platform may not provide sufficient guidance on hardware-specific testing, where practical constraints diverge from theoretical models."],"source":"enrich:decision_facts","observed_at":"2026-07-17T03:17:14.771Z"},"constraint_facets":{"min_ram_gb":null,"pricing_model":"freemium","requires_docker":false},"decision_summary":[{"label":"Pricing","value":"freemium - The repository is free to use under the Apache-2.0 license. However, external resources linked might have their own licensing terms or costs."},{"label":"Adopt for","value":"awesome-ai-safety is a curated list of papers and technical articles focused on ensuring AI quality and safety across various machine learning domains including CV and NLP."}]}}