machine unlearning
Machine unlearning refers to methods that allow a machine learning model to forget specific training data without retraining from scratch. This capability is particularly important for privacy and compliance, enabling models to respect data removal requests.
- A Reliable Cryptographic Framework for Empirical Machine Unlearning Evaluation
- Ascent Fails to Forget
- CoUn: Empowering Machine Unlearning via Contrastive Learning
- Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness
- DualOptim: Enhancing Efficacy and Stability in Machine Unlearning with Dual Optimizers
- Efficient Utility-Preserving Machine Unlearning with Implicit Gradient Surgery
- Efficient Verified Unlearning For Distillation
- FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Model
- Feature Unlearning: Theoretical Foundations and Practical Applications with Shuffling
- Hippocampal-like Sequential Editing for Continual Knowledge Updates in Large Language Models
- Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research
- Machine Unlearning in 3D Generation: A Perspective-Coherent Acceleration Framework
- Machine Unlearning under Overparameterization
- Machine Unlearning via Task Simplex Arithmetic
- Position: Bridge the Gaps between Machine Unlearning and AI Regulation
- Probing Hidden Knowledge Holes in Unlearned LLMs
- Quantifying Cross-Modality Memorization in Vision-Language Models
- RUAGO: Effective and Practical Retain-Free Unlearning via Adversarial Attack and OOD Generator
- Rewind-to-Delete: Certified Machine Unlearning for Nonconvex Functions
- The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed Samples
- Unlearning-Aware Minimization
- Wisdom is Knowing What not to Say: Hallucination-Free LLMs Unlearning via Attention Shifting