awesome-safety-critical-ai

A curated list of references on the role of AI in safety-critical systems ⚠️
https://github.com/jgalego/awesome-safety-critical-ai

Last synced: about 19 hours ago
JSON representation

<a id="articles"></a>📝 Articles
- Ukraine's Future Vision and Current Capabilities for Waging AI-Enabled Autonomous Warfare
- Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
- Engineering problems in machine learning systems
- Safety-critical computer vision: an empirical survey of adversarial evasion attacks and defenses on computer vision systems
- Artificial Intelligence for Safety-Critical Systems in Industrial and Transportation Domains: A Survey
- White Paper Machine Learning in Certified Systems
- Artificial intelligence in health care: accountability and safety
- Trustworthy Artificial Intelligence in Medical Imaging
- Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
- A Goal-Directed Dialogue System for Assistance in Safety-Critical Application
- The Increasing Risks of Risk Assessment: On the Rise of Artificial Intelligence and Non-Determinism in Safety-Critical Systems
- AI-supported estimation of safety critical wind shear-induced aircraft go-around events utilizing pilot reports - 0)
- Engineering problems in machine learning systems
- Trustworthy AI: From Principles to Practices
- Understanding and Identifying Challenges in Design of Safety-Critical AI Systems
- Architectural Patterns for Integrating AI Technology into Safety-Critical System
- Safety-critical computer vision: an empirical survey of adversarial evasion attacks and defenses on computer vision systems
- Challenges of Machine Learning Applied to Safety-Critical Cyber-Physical Systems
- Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
- Engineering problems in machine learning systems
- Safety-critical computer vision: an empirical survey of adversarial evasion attacks and defenses on computer vision systems
- Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
- Engineering problems in machine learning systems
- Safety-critical computer vision: an empirical survey of adversarial evasion attacks and defenses on computer vision systems
- Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
- Engineering problems in machine learning systems
- Safety-critical computer vision: an empirical survey of adversarial evasion attacks and defenses on computer vision systems
- Assurance Argument Patterns and Processes for Machine Learning in Safety-Related Systems
- Collaborative Intelligence for Safety-Critical Industries: A Literature Review
- Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
- Engineering problems in machine learning systems
- Safety-critical computer vision: an empirical survey of adversarial evasion attacks and defenses on computer vision systems
- Trustworthy AI - Part I - AI-Part-II-Mariani-Rossi/9f354b3a88e6d6512d22ec152e6c6131a1e44cab) and [III](https://www.semanticscholar.org/paper/Trustworthy-AI-Part-III-Mariani-Rossi/ff446b46c5b9b4c0d18849d479fe5645f6182a36)
- Lessons From Red Teaming 100 Generative AI Products
- Engineering Dependable AI Systems
- Unpacking Human-AI Interaction in Safety-Critical Industries: A Systematic Literature Review
- Requirements Engineering Challenges in Building AI-Based Complex Systems
- Quantification of the Impact of Random Hardware Faults on Safety-Critical AI Applications: CNN-Based Traffic Sign Recognition Case Study
- Resilience of Deep Learning applications: a systematic literature review of analysis and hardening techniques
- Where AI Assurance Might Go Wrong: Initial lessons from engineering of critical systems
- What’s your ML test score? A rubric for ML production systems
- Addressing uncertainty in the safety assurance of machine-learning
- Rethinking the Maturity of Artificial Intelligence in Safety-Critical Settings
- Output range analysis for deep feedforward neural networks
- Safety-critical computer vision: an empirical survey of adversarial evasion attacks and defenses on computer vision systems
- SoK: Security and Privacy in Machine Learning
- Engineering Dependable AI Systems
- Unpacking Human-AI Interaction in Safety-Critical Industries: A Systematic Literature Review
- Requirements Engineering Challenges in Building AI-Based Complex Systems
- Resilience of Deep Learning applications: a systematic literature review of analysis and hardening techniques
- Where AI Assurance Might Go Wrong: Initial lessons from engineering of critical systems
- What’s your ML test score? A rubric for ML production systems
- Addressing uncertainty in the safety assurance of machine-learning
- AI Safety for Physical Infrastructures: A Collaborative and Interdisciplinary Approach
- Machine learning safety: An overview
- The role of AI in detecting and mitigating human errors in safety-critical industries: A review
- Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
- Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems
- Formal Specification and Verification of Autonomous Robotic Systems: A Survey
- Effective Mitigations for Systemic Risks from General-Purpose AI
- Artificial intelligence in safety-critical systems: a systematic review
- A corroborative approach to verification and validation of human-robot teams
- Holistic Safety and Responsibility Evaluations of Advanced AI Models
- A Survey on Failure Analysis and Fault Injection in AI Systems
- Testing and verification of neural-network-based safety-critical control software: A systematic literature review
- Machine Learning Testing: Survey, Landscapes and Horizons
- Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems
- Output range analysis for deep feedforward neural networks
- AI Safety for Physical Infrastructures: A Collaborative and Interdisciplinary Approach
- Machine learning safety: An overview
- The role of AI in detecting and mitigating human errors in safety-critical industries: A review
- Artificial intelligence in health care: accountability and safety
- Trustworthy Artificial Intelligence in Medical Imaging
- Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
- A Goal-Directed Dialogue System for Assistance in Safety-Critical Application
- The Increasing Risks of Risk Assessment: On the Rise of Artificial Intelligence and Non-Determinism in Safety-Critical Systems
- AI-supported estimation of safety critical wind shear-induced aircraft go-around events utilizing pilot reports - 0)
- Engineering problems in machine learning systems
- Automated Verification of Neural Networks: Advances, Challenges and Perspectives
- Machine Learning Testing: Survey, Landscapes and Horizons
- Engineering problems in machine learning systems
- Automated Verification of Neural Networks: Advances, Challenges and Perspectives
- Trustworthy AI: From Principles to Practices
- Understanding and Identifying Challenges in Design of Safety-Critical AI Systems
- Formal Specification and Verification of Autonomous Robotic Systems: A Survey
- Large-scale machine learning systems in real-world industrial settings: A review of challenges and solutions
- Safety-critical computer vision: an empirical survey of adversarial evasion attacks and defenses on computer vision systems
- SoK: Security and Privacy in Machine Learning
- Challenges of Machine Learning Applied to Safety-Critical Cyber-Physical Systems
- Collaborative Intelligence for Safety-Critical Industries: A Literature Review
- Hidden Technical Debt in Machine Learning Systems
- Towards Verified Artificial Intelligence
- Expert-in-the-loop Systems Towards Safety-critical Machine Learning Technology in Wildfire Intelligence
- Hidden Technical Debt in Machine Learning Systems
- Towards Verified Artificial Intelligence
- Neural Bridge Sampling for Evaluating Safety-Critical Autonomous Systems
- Expert-in-the-loop Systems Towards Safety-critical Machine Learning Technology in Wildfire Intelligence
- Effective Mitigations for Systemic Risks from General-Purpose AI
- A corroborative approach to verification and validation of human-robot teams
- Holistic Safety and Responsibility Evaluations of Advanced AI Models
- A Survey on Failure Analysis and Fault Injection in AI Systems
- Testing and verification of neural-network-based safety-critical control software: A systematic literature review
- Engineering problems in machine learning systems
- Formal-LLM: Integrating Formal Language and Natural Language for Controllable LLM-based Agents
- Safety-critical computer vision: an empirical survey of adversarial evasion attacks and defenses on computer vision systems
- Understanding and Avoiding AI Failures: A Practical Guide
- Machine Learning and Software Product Assurance: Bridging the Gap
- The Fusion of Large Language Models and Formal Methods for Trustworthy AI Agents: A Roadmap
- The Brittleness of AI-Generated Image Watermarking Techniques: Examining Their Robustness Against Visual Paraphrasing Attacks
- AI at work – Mitigating safety and discriminatory risk with technical standards
- Can Large Language Models Transform Natural Language Intent into Formal Method Postconditions?
- Assurance for Autonomy – JPL’s past research, lessons learned, and future directions
- Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
- Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
- Engineering problems in machine learning systems
- Safety-critical computer vision: an empirical survey of adversarial evasion attacks and defenses on computer vision systems
- Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competition
- The Prompt Report: A Systematic Survey of Prompt Engineering Techniques
- Datasheets for Datasets
- Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
- Engineering problems in machine learning systems
- Safety-critical computer vision: an empirical survey of adversarial evasion attacks and defenses on computer vision systems
- Model cards for model reporting
- Data Cards: Purposeful and Transparent Dataset Documentation for Responsible AI
- A Review of Formal Methods applied to Machine Learning
- How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review
- Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
- Engineering problems in machine learning systems
- Safety-critical computer vision: an empirical survey of adversarial evasion attacks and defenses on computer vision systems
<a id="books"></a>📚 Books
- Machine Learning Safety
- Artificial Intelligence for Safety and Reliability Engineering: Methods, Applications, and Challenges
- Artificial Intelligence for Safety and Reliability Engineering: Methods, Applications, and Challenges
- Machine Learning Safety
- Artificial Intelligence for Safety and Reliability Engineering: Methods, Applications, and Challenges
- Machine Learning Safety
- Artificial Intelligence for Safety and Reliability Engineering: Methods, Applications, and Challenges
- Machine Learning Safety
- Artificial Intelligence for Safety and Reliability Engineering: Methods, Applications, and Challenges
- Machine Learning Safety
- Interpretable Machine Learning: A Guide for Making Black Box Models Explainable
- Artificial Intelligence for Safety and Reliability Engineering: Methods, Applications, and Challenges
- Artificial Intelligence for Safety and Reliability Engineering: Methods, Applications, and Challenges
- Trust in Machine Learning
- Reliable Machine Learning: Applying SRE Principles to ML in Production
- Machine Learning Safety
- Designing Machine Learning Systems: An Iterative Process for Production-Ready Applications
- Machines We Trust: Perspectives on Dependable AI
- Artificial Intelligence for Safety and Reliability Engineering: Methods, Applications, and Challenges
- Trust in Machine Learning
- Adversarial Machine Learning
- Machines We Trust: Perspectives on Dependable AI
- Machine Learning Safety
- Designing Machine Learning Systems: An Iterative Process for Production-Ready Applications
- Machine Learning Safety
- Software for Dependable Systems: Sufficient Evidence?
- Artificial Intelligence for Safety and Reliability Engineering: Methods, Applications, and Challenges
- Machine Learning Safety
- Artificial Intelligence for Safety and Reliability Engineering: Methods, Applications, and Challenges
- Machine Learning Safety
- Artificial Intelligence for Safety and Reliability Engineering: Methods, Applications, and Challenges
- Reliable Machine Learning: Applying SRE Principles to ML in Production
- Machine Learning Safety
- Artificial Intelligence for Safety and Reliability Engineering: Methods, Applications, and Challenges
- Machine Learning Safety
<a id="standards"></a>📐 Standards
- Generic
  - SAE G-34
  - ISO/IEC 38507:2022
  - ISO/IEC 42001:2023
  - ANSI/UL 4600
  - IEEE 7009-2024 - Safe Design of Autonomous and Semi-Autonomous Systems
  - ISO/IEC 23053:2022
  - ISO/IEC 23894:2023
  - ISO/IEC 38507:2022
  - ISO/IEC 42001:2023
  - ISO/IEC JTC 1/SC 42
  - NIST AI 100-1
  - ANSI/UL 4600
  - IEEE 7009-2024 - Safe Design of Autonomous and Semi-Autonomous Systems
  - ISO/IEC 23053:2022
  - ISO/IEC 23894:2023
- Coding
  - C Language Edition
  - `BARR-C:2018`
  - `AUTOSAR` - related systems
  - `BARR-C:2018`
  - C Language Edition
  - C++ Language Edition
  - `HIC++`
  - `JSF AV C++`
  - `JPL C`
  - `MISRA-C:«/2004`
  - `MISRA-C/2012`
  - `MISRA-C++/2008`
  - Rules for secure C software development
  - `SEI CERT`
<a id="blogs"></a>✍️ Blogs
- When Doctors With AI Are Outperformed by AI Alone
- Designing Effective Policies for Safety-Critical AI
- Designing Effective Policies for Safety-Critical AI
- Verifying and validating AI in safety-critical systems
- Unpacking Human-AI Interaction in Safety-Critical Industries: A Systematic Literature Review
- Breaking things is easy
- Building safe artificial intelligence: specification, robustness, and assurance
- Can We Trust AI in Safety Critical Systems?
- The impact of AI/ML on qualifying safety-critical software
- Part 2: Reflections On AI (Historical Safety Critical Systems)
- When Doctors With AI Are Outperformed by AI Alone
- Artificial Intelligence, Critical Systems, and the Control Problem
- How is AI being used in Aviation?
- The Road to AI Certification: The importance of Verification and Validation in AI
- The Surprising Brittleness of AI
- Safety In Critical AI Systems
- The risks and benefits of AI translations in safety-critical industries
- Building safe artificial intelligence: specification, robustness, and assurance
- The Surprising Brittleness of AI
- Safety In Critical AI Systems
- Artificial Intelligence in Safety-Critical Systems
- The impact of AI/ML on qualifying safety-critical software
- When Doctors With AI Are Outperformed by AI Alone
- Artificial Intelligence, Critical Systems, and the Control Problem
- AI Governance Mega-map: Safe, Responsible AI and System, Data & Model Lifecycle
- AI Red Teaming: Securing Unpredictable Systems
- What is AI Red Teaming?
- The Expanding Role of Red Teaming in Defending AI Systems
- What is AI Red Teaming?
- Verifying and validating AI in safety-critical systems
- Unpacking Human-AI Interaction in Safety-Critical Industries: A Systematic Literature Review
- Breaking things is easy
- Can We Trust AI in Safety Critical Systems?
- Artificial Intelligence in Safety-Critical Systems
<a id="miscellaneous"></a>👾 Miscellaneous
- Bleeding Edge ⚗️
  - DHS AI
  - NIST
  - NVIDIA
  - CO/AI
  - Hacker News on The Best Language for Safety-Critical Software
  - MITRE ATLAS - world insights
  - CO/AI, actionable resources & strategies for the AI era
  - CISA's Roadmap for Artificial Intelligence
  - Google's Responsible Generative AI Toolkit
  - Hacker News on The Best Language for Safety-Critical Software
  - MITRE ATLAS to navigate threats to AI systems through real-world insights
  - OWASP's Top 10 LLM Applications & Generative AI
  - Paul Niquette's Software Does Not Fail essay
  - RobustML - run hub for learning about robust ML
  - SEBoK Verification and Validation of Systems in Which AI is a Key Element
  - StackOverflow discussion on Python coding standards for Safety Critical applications
  - Deloitte
  - IBM
  - Microsoft
  - AI Incident Database
  - AI Safety
  - AI Safety Atlas
  - DARPA's Assured Autonomy Tools Portal
  - Awful AI
  - OWASP's Top 10 LLM Applications & Generative AI
  - Avid - source, extensible knowledge base of AI failures
  - Data Cards Playbook
  - ECSS's Space engineering – Machine learning qualification handbook
  - ML Safety
  - AI Safety Landscape
  - AI Safety Quest - minded people and find projects that are a good fit for their skills
  - AI Safety Support - building project working to reduce the likelihood of existential risk from AI by providing resources, networking opportunities and support to early career, independent and transitioning researchers
  - AI Snake Oil
  - Awful AI
  - MLSecOps
<a id="roadmaps"></a>🛣️ Roadmaps
- Roadmaps for AI Integration in the Rail Sector
- Roadmap for Artificial Intelligence Safety Assurance
- Roadmap for Artificial Intelligence - of-agency plan aligned with national AI strategy
- Artificial Intelligence Roadmap - centric approach to AI in aviation
<a id="reports"></a>📋 Reports
- State of AI Agents
- Superagency in the workplace: Empowering people to unlock AI’s full potential
- State of AI Report 2024
- The Flight to Safety-Critical AI: Lessons in AI Safety from the Aviation Industry
- AI Safety Index 2024
- Responsible AI Progress Report 2025
- International AI Safety Report 2025
- State of AI Report 2024
- Responsible AI Transparency Report 2024
- Examining Proposed Uses of LLMs to Produce or Assess Assurance Arguments
- US Responsible AI Survey
- AI Safety Index 2024
- Responsible AI Progress Report 2025
- International AI Safety Report 2025
- Superagency in the workplace: Empowering people to unlock AI’s full potential
- Responsible AI Transparency Report 2024
- US Responsible AI Survey
<a id="tools"></a>🛠️ Tools
- Adversarial Attacks
  - `bethgelab/foolbox`
  - `Trusted-AI/adversarial-robustness-toolbox` - evasion, poisoning, extraction, inference - red and blue teams
  - `bethgelab/foolbox`
  - `Trusted-AI/adversarial-robustness-toolbox` - evasion, poisoning, extraction, inference - red and blue teams
- Data Management
  - `cleanlab/cleanlab` - centric AI package for data quality and ML with messy, real-world data and labels.
  - `facebook/Ax` - purpose platform for understanding, managing, deploying, and automating adaptive experiments
  - `great-expectations/great_expectations`
  - `cleanlab/cleanlab` - centric AI package for data quality and ML with messy, real-world data and labels.
  - `facebook/Ax` - purpose platform for understanding, managing, deploying, and automating adaptive experiments
  - `great-expectations/great_expectations`
  - `iterative/dvc`
  - `pydantic/pydantic`
  - `tensorflow/data-validation`
  - `unionai-oss/pandera`
- Model Evaluation
  - `confident-ai/deepeval` - to-use, open-source LLM evaluation framework, for evaluating and testing LLM systems
  - `RobustBench/robustbench`
  - `trust-ai/SafeBench` - critical scenarios
  - `confident-ai/deepeval` - to-use, open-source LLM evaluation framework, for evaluating and testing LLM systems
  - `RobustBench/robustbench`
  - `trust-ai/SafeBench` - critical scenarios
- Oldies 🕰️
  - `pralab/secml`
- Bleeding Edge ⚗️
  - `langgenius/dify` - source LLM app development platform, which combines agentic AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production
  - `latitude-dev/latitude-llm` - source prompt engineering platform to build, evaluate, and refine your prompts with AI
  - `agno-agi/agno` - modal agents
  - `Arize-ai/phoenix` - source AI observability platform designed for experimentation, evaluation, and troubleshooting
  - `BerriAI/litellm`
  - `browser-use/browser-use`
  - `Cinnamon/kotaemon` - source RAG-based tool for chatting with your documents
  - `ComposioHQ/composio` - quality integrations via function calling
  - `deepset-ai/haystack` - ready LLM applications
  - `dottxt-ai/outlines`
  - `agno-agi/agno` - modal agents
  - `Arize-ai/phoenix` - source AI observability platform designed for experimentation, evaluation, and troubleshooting
  - `ComposioHQ/composio` - quality integrations via function calling
  - `deepset-ai/haystack` - ready LLM applications
  - `dottxt-ai/outlines`
  - `exo-explore/exo`
  - `FlowiseAI/Flowise`
  - `groq/groq-python`
  - `guidance-ai/guidance`
  - `h2oai/h2o-llmstudio` - code GUI for fine-tuning LLMs
  - `hiyouga/LLaMA-Factory` - tuning of 100+ LLMs and VLMs
  - `instructor-ai/instructor`
  - `keephq/keep` - source AIOps and alert management platform
  - `khoj-ai/khoj` - hostable AI second brain
  - `ItzCrazyKns/Perplexica` - powered search engine and open source alternative to Perplexity AI
  - `langfuse/langfuse`
  - `h2oai/h2o-llmstudio` - code GUI for fine-tuning LLMs
  - `hiyouga/LLaMA-Factory` - tuning of 100+ LLMs and VLMs
  - `instructor-ai/instructor`
  - `khoj-ai/khoj` - hostable AI second brain
  - `run-llama/llama_index` - powered agents over your data
  - `stanfordnlp/dspy` - not prompting - language models
  - `topoteretes/cognee`
  - `unitaryai/detoxify`
  - `unslothai/unsloth` - R1 and reasoning LLMs 2x faster with 70% less memory! 🦥
  - `microsoft/data-formulator`
  - `microsoft/prompty`
  - `Mintplex-Labs/anything-llm` - in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, and more
  - `ollama/ollama` - R1, Phi-4, Gemma 2, and other large LMs
  - `promptfoo/promptfoo` - friendly local tool for testing LLM applications
  - `run-llama/llama_index` - powered agents over your data
  - `ScrapeGraphAI/Scrapegraph-ai`
  - `stanfordnlp/dspy` - not prompting - language models
  - `unslothai/unsloth` - R1 and reasoning LLMs 2x faster with 70% less memory! 🦥
  - `Giskard-AI/giskard`
  - `DS4SD/docling`
  - `eth-sri/lmql`
  - `exo-explore/exo`
  - `FlowiseAI/Flowise`
  - `groq/groq-python`
  - `guidance-ai/guidance`
- Model Fairness & Privacy
- Model Intepretability
- Model Lifecycle
  - `aimhubio/aim` - to-use and supercharged open-source experiment tracker
  - `comet-ml/opik` - source platform for evaluating, testing and monitoring LLM applications
  - `comet-ml/opik` - source platform for evaluating, testing and monitoring LLM applications
  - `evidentlyai/evidently` - source ML and LLM observability framework
  - `IDSIA/sacred`
  - `mlflow/mlflow` - source platform for the ML lifecycle
  - `wandb/wandfb` - featured AI developer platform
  - `evidentlyai/evidently` - source ML and LLM observability framework
  - `mlflow/mlflow` - source platform for the ML lifecycle
  - `wandb/wandfb` - featured AI developer platform
- Model Security
  - `azure/PyRIT`
  - `ffhibnese/Model-Inversion-Attack-ToolBox`
  - `protectai/llm-guard`
  - `ffhibnese/Model-Inversion-Attack-ToolBox`
  - `protectai/llm-guard`
  - `nvidia/garak` - teaming and assessment kit
  - `azure/PyRIT`
- Model Testing & Validation
  - `deepchecks/deepchecks` - source package for validating ML models and data
  - `explodinggradients/ragas` - driven insights for LLM apps
  - `pytorchfi/pytorchfi`
  - `deepchecks/deepchecks` - source package for validating ML models and data
  - `explodinggradients/ragas` - driven insights for LLM apps
  - `pytorchfi/pytorchfi`
- Miscellaneous
  - `microsoft/robustlearn`
  - `microsoft/robustlearn`
<a id="initiatives"></a>🤝 Initiatives
- Future of Life Institute
- Foundations of responsible data management
- Dependable, Certifiable & Explainable Artificial Intelligence for Critical Systems
- Best practices for trustworthy AI in medicine
- AI for Critical Systems Competence Center
- AI for Good
- Safety Critical AI
- Sustainable Machine Learning
- Responsible AI Institute
- Responsible AI Institute
- Center for Responsible AI
- WASP WARA Public Safety
- Foundations of responsible data management
- Dependable, Certifiable & Explainable Artificial Intelligence for Critical Systems
- AI for Critical Systems Competence Center
- AI for Good
- Safety Critical AI
<a id="tldr"></a>🏃 TLDR
- NotebookLM
- NotebookLM
<a id="top-picks"></a>🌟 Editor's Choice
- high-interest credit card of technical debt
- tools for production-ready ML
- trustworthy AI
- red teaming hundreds of generative AI products
<a id="meta"></a>🏁 Meta
- Bleeding Edge ⚗️
  - safety-critical-systems
  - Awesome LLM Apps
  - Awesome Python Data Science
  - Awesome MLOps
  - Awesome Production ML
  - Awesome Trustworthy AI - of-distribution generalization, adversarial examples, backdoor attack, model inversion attack, machine unlearning, &c.
  - Awesome Responsible AI - Centered AI
  - Awesome Safety Critical - critical software
  - FDA Draft Guidance on AI
<a id="certifications"></a>📜 Certifications
- Certified Tester AI Testing (CT-AI)
- Certified AI Scientist (CAIS)
- Certified Tester AI Testing (CT-AI)
- Certified AI Scientist (CAIS)
<a id="conferences"></a>🎤 Conferences
- 20th European Dependable Computing Conference
- Workshop on Sociotechnical AI Safety
- AI for Critical Infrastructure
- Trustworthy machine learning
- FAA Artificial Intelligence Safety Assurance: Roadmap and Technical Exchange Meetings
- AI/ML Components in Safety-Critical Aviation Systems: Selected Concepts and Underlying Principles
- Developing Standards for AI/ML Systems in Civil Aviation: Challenges and Barriers
- FAA Artificial Intelligence Safety Assurance: Roadmap and Technical Exchange Meetings
- AI/ML Components in Safety-Critical Aviation Systems: Selected Concepts and Underlying Principles
- Developing Standards for AI/ML Systems in Civil Aviation: Challenges and Barriers
- NFM Workshop on AI Safety
- LLMs in Production 2023
- 32nd annual Safety-Critical Systems Symposium
- AI in Production 2024
- ML:Integrity 2022
- 32nd annual Safety-Critical Systems Symposium
- 20th European Dependable Computing Conference
- Robust ML Workshop 2024
- Workshop on Sociotechnical AI Safety
- Trustworthy machine learning
- Safety Critical Systems Symposium SSS'25
- South Wales Safety Groups Alliance Conference and Exhibition
<a id="courses"></a>👩‍🏫 Courses
- Machine Learning in Production - Mellon University
- Trustworthy Machine Learning
- Trustworthy Machine Learning
- AI for Good Specialization
- AI Red Teaming
- AI for Good Specialization
- AI Red Teaming
- Dependable AI Systems - Champaign
- Limits to Prediction
- Machine Learning for Healthcare
- Machine Learning in Production - Mellon University
- Responsible AI
- Robustness in Machine Learning
- Security and Privacy of Machine Learning
- Trustworthy Artificial Intelligence
- Trustworthy Machine Learning
- Machine Learning for Healthcare
- Responsible AI
- Robustness in Machine Learning
- Security and Privacy of Machine Learning
- Trustworthy Artificial Intelligence
- AI for Social Good
- Introduction to AI Safety
- Real-Time Mission-Critical Systems Design
- Safety Critical Systems
- Safety Critical Systems
- Dependable AI Systems - Champaign
- Limits to Prediction
<a id="guidelines"></a>📙 Guidelines
- Reponsible AI Guidelines
- Ethics guidelines for trustworthy AI
- The EU AI Act
- AI Principles
- SAIF // Secure AI Framework: A practitioner’s guide to navigating AI security
- Initial guidelines for the use of Generative AI tools at Harvard
- Roles and Responsibilities Framework for Artificial Intelligence in Critical Infrastructure
- Safety and Security Guidelines for Critical Infrastructure Owners and Operators
- SAIF // Secure AI Framework: A practitioner’s guide to navigating AI security
- Universal Guidelines for AI
- Reponsible AI Guidelines
- Ethics guidelines for trustworthy AI
- The EU AI Act
- AI Principles
- Initial guidelines for the use of Generative AI tools at Harvard
- Roles and Responsibilities Framework for Artificial Intelligence in Critical Infrastructure
- Safety and Security Guidelines for Critical Infrastructure Owners and Operators
- Responsible AI: Principles and Approach
- JSP 936: Dependable Artificial Intelligence (AI) in defense (part 1: directive)
- AI Principles
- Responsible AI at Stanford
- Artificial Intelligence/Machine Learning System Safety
- Guidelines for AI in Parliaments
- Responsible AI: Principles and Approach
- JSP 936: Dependable Artificial Intelligence (AI) in defense (part 1: directive)
- Guidelines for secure AI system development
- AI Principles
- Responsible AI at Stanford
<a id="working-groups"></a>👷🏼 Working Groups
- Bleeding Edge ⚗️
<a id="videos"></a>📺 Videos
- Bleeding Edge ⚗️
<a id="whitepapers"></a>📄 Whitepapers
- Bleeding Edge ⚗️
Contributions
- Bleeding Edge ⚗️
  - issues - safety-critical-ai/pulls) or [discussions](https://github.com/JGalego/awesome-safety-critical-ai/discussions).
About Us
- Bleeding Edge ⚗️
  - Critical Software - and mission-critical software.
  - open roles

Programming Languages

Python 88 Jupyter Notebook 12 TypeScript 8 HTML 2 Go 1 JavaScript 1 CSS 1

awesome-safety-critical-ai

<a id="articles"></a>📝 Articles

<a id="books"></a>📚 Books

<a id="standards"></a>📐 Standards

Generic

Coding

<a id="blogs"></a>✍️ Blogs

<a id="miscellaneous"></a>👾 Miscellaneous

Bleeding Edge ⚗️

<a id="roadmaps"></a>🛣️ Roadmaps

<a id="reports"></a>📋 Reports

<a id="tools"></a>🛠️ Tools

Adversarial Attacks

Data Management

Model Evaluation

Oldies 🕰️

Bleeding Edge ⚗️

Model Fairness & Privacy

Model Intepretability

Model Lifecycle

Model Security

Model Testing & Validation

Miscellaneous

<a id="initiatives"></a>🤝 Initiatives

<a id="tldr"></a>🏃 TLDR

<a id="top-picks"></a>🌟 Editor's Choice

<a id="meta"></a>🏁 Meta

Bleeding Edge ⚗️

<a id="certifications"></a>📜 Certifications

<a id="conferences"></a>🎤 Conferences

<a id="courses"></a>👩‍🏫 Courses

<a id="guidelines"></a>📙 Guidelines

<a id="working-groups"></a>👷🏼 Working Groups

Bleeding Edge ⚗️

<a id="videos"></a>📺 Videos

Bleeding Edge ⚗️

<a id="whitepapers"></a>📄 Whitepapers

Bleeding Edge ⚗️

Contributions

Bleeding Edge ⚗️

About Us

Bleeding Edge ⚗️