忘记一个人意味着什么？视觉-语言模型中的个体级遗忘
What Does It Mean to Forget a Person? Individual-Level Unlearning in Vision-Language Models
浏览论文内容
中文总结 AI 辅助
针对视觉-语言模型中个体级遗忘缺失，提出首个基准IDUnlearn-Bench，评估四类任务，发现属性遗忘无法彻底消除身份知识，揭示信息遗忘与整体遗忘的鸿沟。
中文摘要 AI 辅助
从视觉-语言模型（VLMs）中擦除个体身份具有独特的挑战性，因为个人数据在多种模态间纠缠，而非作为孤立的属性存储。然而，现有的多模态遗忘基准主要评估以属性为中心的遗忘，忽视了更关键的个体级遗忘目标：消除模型跨模态访问、关联和重建目标相关信息的能力。为弥补这一空白，我们提出了IDUnlearn-Bench，这是首个针对VLM中个体级多模态遗忘的基准。它将每个个体表示为连接的多模态证据，并评估四个任务族：属性访问、身份访问、身份绑定和身份重建。在代表性VLM和遗忘方法上的实验表明，成功的以属性为中心的遗忘往往留下大量身份级知识完好无损，且可能是非单调的：降低一种风险形式可能放大另一种。模型可能抑制选定信息，同时仍能识别目标、关联记录或重建个体。这些发现揭示了遗忘关于一个人的信息与遗忘这个整体的人之间的根本差距。
英文摘要
Erasing individual identities from Vision-Language Models (VLMs) is uniquely challenging because personal data is entangled across modalities rather than stored as isolated attributes. However, existing multimodal unlearning benchmarks primarily evaluate attribute-centric forgetting, overlooking the more critical objective of individual-level unlearning: eliminating a model's ability to access, link, and reconstruct target-related information across modalities. To address this gap, we propose IDUnlearn-Bench, the first benchmark for individual-level multimodal unlearning in VLMs. It represents each individual as connected multimodal evidence and evaluates four task families: attribute access, identity access, identity binding, and identity reconstruction. Experiments on representative VLMs and unlearning methods show that successful attribute-centric forgetting often leaves substantial identity-level knowledge intact and can be non-monotonic: reducing one form of risk may amplify another. Models may suppress selected information while still identifying the target, linking records, or reconstructing the individual. These findings reveal a fundamental gap between forgetting information about a person and forgetting the person as a whole.
发表机构
- Xidian University（西安电子科技大学）
- Nanyang Technological University（南洋理工大学）
机构由 AI 辅助整理，请以论文原文为准。
