I-CARE：针对文本到图像模型的可控、多样且具代表性的遗忘场景中与干扰相关现象的分析
I-CARE: Analysis of interference-related phenomena in a controllable, diverse and representative unlearning setting for text-to-image models
- Universidad Autónoma de Madrid（马德里自治大学）
- Universidad Politécnica de Madrid（马德里理工大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出I-CARE方法论，将干扰形式化为生成式遗忘的首要研究对象，通过形式化定义支持系统研究，经可行性验证具备实际适用性，配套开源框架与网页界面便于结果探索。
AI中文摘要：
机器遗忘研究的是从AI模型中移除知识，使系统遗忘其先前学习的某个概念。尽管生成式机器遗忘领域进展迅速，但应保留的语义相关概念出现的意外退化（以下简称干扰）仍缺乏充分的特征刻画与一致的评估方式。本文提出I-CARE，一种将干扰形式化为生成式遗忘中首要研究对象的方法论。I-CARE未提出新的基准或遗忘算法，而是为任务、指标及结果报告模板提供了形式化定义，支持在各类遗忘场景中对干扰进行系统且可复现的研究。该方法论旨在在模型与遗忘算法演进时仍保持有效性，将长期科学洞见与短期经验结果解耦；同时，本文采用最先进的算法与常用数据集开展了可行性验证，结果表明I-CARE可在多个遗忘场景中对干扰模式进行有意义的分析，确立了该框架的实际适用性。该方法论的软件实现以开源框架形式提供，附带基于网页的图形界面，无需直接与代码库或专业数据分析工具交互即可探索本研究的结果。
英文摘要：
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.
