Practical Fairness

Spis treści ebooka

• Preface
  • Goals of This Book
  • Practical Notes on the Book
  • Conventions Used in This Book
  • Using Code Examples
  • OReilly Online Learning
  • How to Contact Us
  • Acknowledgments
• 1. Fairness, Technology, and the Real World
  • Fairness in Engineering Is an Old Problem
  • Our Fairness Problems Now
    • Community Norms
    • Equity and Equality
    • Security
    • Privacy
      • Information collection
      • Information processing
      • Information dissemination
      • Invasion
      • A way of thinking about privacy: contextual integrity
  • Legal Responses to Fairness in Technology
  • The Assumptions and Approaches in This Book
  • What If Im Skeptical of All This Fairness Talk?
    • Wont Fairness Slow Down Innovation?
    • Are There Any Real-World Consequences for Not Developing Fairness-Aware Practices?
  • What Is Fairness?
  • Rules to Code By
• 2. Understanding Fairness and the Data Science Pipeline
  • Metrics for Fairness
    • Measures of Equity
      • Antidiscrimination measures of equity
      • Rationality measures of equity
    • Measures of Privacy
      • Technical measures of privacy protection
        • k-anonymity
        • Differential privacy
      • Human measures of privacy protection
    • Measures of Security
  • Connected Concepts
    • Privacy and Security
    • Privacy and Equity
    • Equality and Security
    • Accuracy and Fairness
  • Automated Fairness?
  • Checklist of Points of Entry for Fairness in the Data Science Pipeline
  • Concluding Remarks
• 3. Fair Data
  • Ensuring Data Integrity
    • True Measurements
      • Proxies
      • Failures of external validity
      • Undescribed variation
    • Proportionality and Sampling Technique
      • Biased sampling
      • Data duplication
  • Choosing Appropriate Data
    • Equity
      • Fair play
      • Reasonable expectations
    • Privacy
      • Personal data
      • Metadata collection
      • Proxies for private information
    • Security
      • Data collected from the wild is dangerous
      • Inherently dangerous data
      • Naively chosen data
      • Incomplete data
  • Case Study: Choosing the Right Question for a Data Set and the Right Data Set for a Question
  • Quality Assurance for a Data Set: Identifying Potential Discrimination
  • A Timeline for Fairness Interventions
  • Comprehensive Data-Acquisition Checklist
  • Concluding Remarks
• 4. Fairness Pre-Processing
  • Simple Pre-Processing Methods
  • Suppression: The Baseline
  • Massaging the Data Set: Relabeling
  • AIF360 Pipeline
    • Loading the Data
    • Fairness Metrics
  • The US Census Data Set
  • Suppression
  • Reweighting
    • How It Works
    • Code Demonstration
  • Learning Fair Representations
    • How It Works
    • Code Demonstration
  • Optimized Data Transformations
    • How It Works
    • Code Demonstration
  • Fairness Pre-Processing Checklist
  • Concluding Remarks
• 5. Fairness In-Processing
  • The Basic Idea
  • The Medical Data Set
  • Prejudice Remover
    • How It Works
    • Code Demonstration
  • Adversarial Debiasing
    • How It Works
    • Code Demonstration
  • In-Processing Beyond Antidiscrimination
  • Model Selection
  • Concluding Remarks
• 6. Fairness Post-Processing
  • Post-Processing Versus Black-Box Auditing
  • The Data Set
  • Equality of Opportunity
    • How It Works
    • Code Demonstration
  • Calibration-Preserving Equalized Odds
    • How It Works
    • Code Demonstration
  • Concluding Remarks
• 7. Model Auditing for Fairness and Discrimination
  • The Parameters of an Audit
  • Scoping: What Should We Audit?
  • Black-Box Auditing
    • Running a Model Through Different Counterfactuals
    • Model of the Model
    • Auditing Black-Box Models for Indirect Influence
      • How it works
      • Code demonstration
        • The data set
        • A vanilla audit with default library options
        • A black-box model audit
  • Concluding Remarks
• 8. Interpretable Models and Explainability Algorithms
  • Interpretation Versus Explanation
  • Interpretable Models
    • GLRM: How It Works
    • Code Demonstration
  • Explainability Methods
    • SHAP and LIME: The Workhorses for Local Post Hoc Explanations
      • LIME
        • How it works
        • Code example
      • SHAP
        • How it works
        • Code example
    • Data-Driven Explanation
      • How it works
      • Code example
    • Explainability Metrics
  • What Interpretation and Explainability Miss
    • Attacks on Explainable Machine Learning
  • Interpretation and Explanation Checklist
  • Concluding Remarks
• 9. ML Models and Privacy
  • Membership Attacks
    • How It Works
    • Code Demonstration
  • Other Privacy Problems and Attacks
  • Important Privacy Techniques
  • Concluding Remarks
• 10. ML Models and Security
  • Evasion Attacks
    • How It Works
    • Code Demonstration
    • Defending Against Adversarial Attacks
    • Some Evasion Attack Packages
    • Why Do Evasion Attacks Matter to You?
  • Poisoning Attacks
    • How They Work
    • Defenses Against Poisoning Attacks
    • Some Poisoning Attack Packages
    • Why Do Poisoning Attacks Matter to You?
  • Concluding Remarks
• 11. Fair Product Design and Deployment
  • Reasonable Expectations
    • Expectations of Moving Targets
    • Clear Communication
  • Fiduciary Obligations
  • Respecting Traditional Spheres of Privacy and Private Life
  • Value Creation
  • Complex Systems
    • The Impact of the Product Life Cycle
    • The Need for Record Keeping
    • The Need for Experts
  • Clear Security Promises and Delineated Limitations
    • Reasonable Expectations of Security
  • Possibility of Downstream Control and Verification
    • Verification Systems and Obligations
    • Product Iteration Timelines
    • Tracking Downstream Users
  • Products That Work Better for Privileged People
  • Dark Patterns
  • Fair Products Checklist
  • Concluding Remarks
• 12. Laws for Machine Learning
  • Personal Data
    • GDPR
    • California Consumer Privacy Act
    • Data Broker Laws
  • Algorithmic Decision Making
    • GDPR
    • Proposed US Laws for Algorithms
  • Security
    • HIPAA
    • FTC Guidance on Cybersecurity
    • Tort Law
  • Logical Processes
    • Right to an Explanation
    • Freedom of Information Laws
    • Due Process
  • Some Application-Specific Laws
    • Biometrics
    • Local Ordinances on Facial Recognition
    • Chat Bots
  • Concluding Remarks
• Index

pokaż cały spis treści

ukryj recenzje