CAF'E: Causal Black-Box Testing of Machine Unlearning

arXiv:2509.16525 · cs.SE, cs.AI, cs.LG · Submitted 2025-09-20 · Read on arXiv

cs.SE, cs.AI, cs.LG

Submitted: 2025-09-20

Updated: 2026-10-08

Terminology

• Machine Unlearning — 3× in this paper · explained in 3 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Adaptability — 1× in this paper · explained in 1 episode

Sources

• AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias
• Towards Adversarial Evaluations for Inexact Machine Unlearning
• Efficient Attribute Unlearning: Towards Selective Removal of Input Attributes from Feature Representations
• Measuring Forgetting of Memorized Training Examples
• IncomeSCM: From tabular data set to time-series simulator and causal estimation benchmark
• Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
• Machine Unlearning: A Comprehensive Survey

Related papers

• Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
• GitSkills: A Dataset of Agent Skills on GitHub
• SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
• PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
• IntentCoding: Amplifying User Intent in Code Generation
• Incentives and Outcomes in Bug Bounties