I-CARE: Analysis of interference-related phenomena in a controllable, diverse and representative unlearning setting for text-to-image models
Summary
This paper introduces I-CARE, a methodology for systematically analyzing interference in machine unlearning for text-to-image models, providing formal definitions and an open-source framework to enable reproducible study.
View Cached Full Text
Cached at: 09/02/26, 05:54 AM
# I-CARE: Analysis of interference-related phenomena in a controllable, diverse and representative unlearning setting for text-to-image models Source: [https://arxiv.org/abs/2609.00003](https://arxiv.org/abs/2609.00003) [View PDF](https://arxiv.org/pdf/2609.00003) > Abstract: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\. ## Submission history From: Leonardo Santiago Benitez Pereira \[[view email](https://arxiv.org/show-email/14cfe767/2609.00003)\] **\[v1\]**Wed, 24 Jun 2026 16:24:33 UTC \(34,261 KB\)
Similar Articles
Interference-Aware Multi-Task Unlearning
This paper introduces an interference-aware framework for multi-task machine unlearning, addressing task-level and instance-level interference through task-aware gradient projection and instance-level gradient orthogonalization, achieving effective unlearning on multi-task computer vision benchmarks.
Certifying Concept Unlearning in Text-to-Image Diffusion Models
This paper introduces a certification framework for concept unlearning in text-to-image diffusion models, providing high-confidence guarantees on residual leakage and demonstrating that standard attack-based evaluations often underestimate safety risks.
Similarity-Aware Machine Unlearning
This paper proposes a retain-aware localization method for machine unlearning that reduces collateral damage to semantically similar retained examples, and introduces a retain-similar evaluation set. Experiments on CIFAR-10 with ResNet18 show reduced collateral damage and improved unlearning metrics.
What to Forget in Unlearning? Forget Set Curation for Language Models
This paper explores forget set curation for machine unlearning in language models, introducing a benchmark to evaluate verbatim output suppression and highlighting trade-offs between effectiveness and capability retention.
Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks
A comprehensive survey of methods, datasets, and benchmarks for multimodal unlearning across vision, language, video, and audio, providing a taxonomy and highlighting open problems.