Machine unlearning conflates reversing the influence of specific training examples (untraining) with removing the full underlying distribution or behavior (unlearning).
Feder Cooper, Christopher A
5 Pith papers cite this work. Polarity classification is still indexing.
citation-role summary
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Machine unlearning for online L-BFGS requires aligning the full optimizer state including memory to a counterfactual history without deleted samples rather than parameter correction alone.
Concept filtering of child images from training data offers only limited protection against CSAM generation in text-to-image models, as prompting strategies and fine-tuning can bypass filters even when most child images are removed.
A new extraction technique applied to 200 books and 14 LLMs finds that memorization of full books is rare except in specific high-capacity models where entire texts can be recovered verbatim.
citing papers explorer
-
Is your algorithm unlearning or untraining?
Machine unlearning conflates reversing the influence of specific training examples (untraining) with removing the full underlying distribution or behavior (unlearning).
-
Form and Function: Machine Unlearning as a Problem of Misaligned States
Machine unlearning for online L-BFGS requires aligning the full optimizer state including memory to a counterfactual history without deleted samples rather than parameter correction alone.
-
Evaluating Concept Filtering Defenses against Child Sexual Abuse Material Generation by Text-to-Image Models
Concept filtering of child images from training data offers only limited protection against CSAM generation in text-to-image models, as prompting strategies and fine-tuning can bypass filters even when most child images are removed.
-
Extracting memorized pieces of (copyrighted) books from open-weight language models
A new extraction technique applied to 200 books and 14 LLMs finds that memorization of full books is rare except in specific high-capacity models where entire texts can be recovered verbatim.
- What's on Your Mind? Exploring Privacy of Mental Health Apps