# I-CARE: Analysis of interference-related phenomena in a controllable, diverse and representative unlearning setting for text-to-image models

arXiv: https://arxiv.org/abs/2609.00003 · HTML: https://mlsanity.com/paper/2609.00003/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Vision-language and text-to-image safety, one of 12 directions in LLM safety and security.
- Builds on 11 of its 59 references that are in the map.
- First posted on arXiv 24 Jun 2026.

## Placed in

- LLM safety and security / [Vision-language and text-to-image safety](https://mlsanity.com/safety/vision-language-and-text-to-image-safety/)

## Builds on (most cited first, 11 of 11)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Unified Concept Editing in Diffusion Models](https://mlsanity.com/paper/2308.14761/) (2023)
- [SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation](https://mlsanity.com/paper/2310.12508/) (2023)
- [Sources of Irreproducibility in Machine Learning: A Review](https://mlsanity.com/paper/2204.07610/) (2022)
- [A Large-scale Attribute Dataset for Zero-shot Learning](https://mlsanity.com/paper/1804.04314/) (2018)
- [Holistic Unlearning Benchmark: A Multi-Faceted Evaluation for Text-to-Image Diffusion Model Unlearning](https://mlsanity.com/paper/2410.05664/) (2024)
- [Mechanistic Analysis of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning](https://mlsanity.com/paper/2601.18699/) (2026)
- [More Rigorous Software Engineering Would Improve Reproducibility in Machine Learning Research](https://mlsanity.com/paper/2502.00902/) (2025)
- [SPARE: Self-distillation for PARameter-Efficient Removal](https://mlsanity.com/paper/2602.07058/) (2026)
- [Unlearning-based Neural Interpretations](https://mlsanity.com/paper/2410.08069/) (2024)
- [Spec-Driven AI for Science: The ARIA Framework for Automated and Reproducible Data Analysis](https://mlsanity.com/paper/2510.11143/) (2025)

## Abstract (arXiv)

Machine unlearning studies the removal of knowledge from an AI model, making the system forget a concept it previously learned. Despite rapid progress in generative machine unlearning, the unintended degradation of semantically related concepts that should have been retained (henceforth, interference) remains poorly characterized and inconsistently evaluated. This paper introduces I-CARE, a methodology that formalizes interference as a first-class object of study in generative unlearning. Rather than proposing a new benchmark or unlearning algorithm, I-CARE provides formal definitions for tasks, metrics, and templates for reporting results, enabling the systematic and reproducible study of interference across unlearning settings. While our methodology is designed to remain valid as models and unlearning algorithms evolve, decoupling long-term scientific insight from transient empirical results, we present a feasibility demonstration with state-of-the-art algorithms and frequently used datasets. The results demonstrate that I-CARE enables meaningful analysis of interference patterns across multiple unlearning settings, establishing the practical applicability of the framework. The software implementation of the methodology is provided in an open-source framework, together with a web-based graphical interface that enables exploration of the outcomes of this study without requiring direct interaction with the codebase or specialized data analysis tools.