# DECAF: De-Clustering for Adaptive Representational Unlearning

arXiv: https://arxiv.org/abs/2607.23934 · HTML: https://mlsanity.com/paper/2607.23934/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 20 of its 31 references that are in the map.
- First posted on arXiv 27 Jul 2026.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 20 of 20)

- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Certified Data Removal from Machine Learning Models](https://mlsanity.com/paper/1911.03030/) (2019)
- [Making AI Forget You: Data Deletion in Machine Learning](https://mlsanity.com/paper/1907.05012/) (2019)
- [Amnesiac Machine Learning](https://mlsanity.com/paper/2010.10981/) (2020)
- [Approximate Data Deletion from Machine Learning Models](https://mlsanity.com/paper/2002.10077/) (2020)
- [Model Sparsity Can Simplify Machine Unlearning](https://mlsanity.com/paper/2304.04934/) (2023)
- [Zero-Shot Machine Unlearning](https://mlsanity.com/paper/2201.05629/) (2022)
- [Machine Unlearning: Linear Filtration for Logit-based Classifiers](https://mlsanity.com/paper/2002.02730/) (2020)
- [Machine Unlearning: Taxonomy, Metrics, Applications, Challenges, and Prospects](https://mlsanity.com/paper/2403.08254/) (2024)
- [Decoupled Distillation to Erase: A General Unlearning Method for Any Class-centric Tasks](https://mlsanity.com/paper/2503.23751/) (2025)
- [Towards Scalable Exact Machine Unlearning Using Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2406.16257/) (2024)
- [Feature Unlearning for Pre-trained GANs and VAEs](https://mlsanity.com/paper/2303.05699/) (2023)
- [Unlearning vs. Obfuscation: Are We Truly Removing Knowledge?](https://mlsanity.com/paper/2505.02884/) (2025)
- [Revisiting Machine Unlearning with Dimensional Alignment](https://mlsanity.com/paper/2407.17710/) (2024)
- [ESC: Erasing Space Concept for Knowledge Deletion](https://mlsanity.com/paper/2504.02199/) (2025)
- [A Certified Unlearning Approach without Access to Source Data](https://mlsanity.com/paper/2506.06486/) (2025)
- [POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse](https://mlsanity.com/paper/2511.19339/) (2025)
- [Machine Unlearning on Pre-trained Models by Residual Feature Alignment Using LoRA](https://mlsanity.com/paper/2411.08443/) (2024)

## Abstract (arXiv)

Machine unlearning, which aims to remove the influence of specific training data from a trained model, is a key requirement for privacy, accountability, and adaptive deployment. We argue that many unlearning methods are vulnerable to a simple clustering attack, which can recover class structure in an unsupervised manner, limiting their suitability for continual deployment where removal requests must be handled reliably on demand. To address this, we propose DECAF (DE-Clustering for Adaptive Forgetting), a post-hoc method that operates only on the forget set and is designed to break the cluster. DECAF combines input noise, confidence suppression, and entropy-based output diversification to disrupt the residual feature-space structure associated with forgotten data. On CIFAR-10 with ResNet-18, DECAF attains 0.10% forget-class accuracy, 79.4% retain accuracy, and an AUS of 0.88, surpassing all other baselines. In cluster-based analysis, it attains performance comparable to that of unlearning methods that use the full training set, while being significantly more efficient. Code: https://github.com/ale256/representation_unlearning.