Saved in:
Bibliographic Details
Main Authors: Guang, Jiahui, Zhan, Zexun, Xu, Zhenlin, Gao, Cuiyun, Wang, Haiyan, Li, Jing, Gu, Zhaoquan, Zhang, Yanchun
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.08800
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913106516508672
author Guang, Jiahui
Zhan, Zexun
Xu, Zhenlin
Gao, Cuiyun
Wang, Haiyan
Li, Jing
Gu, Zhaoquan
Zhang, Yanchun
author_facet Guang, Jiahui
Zhan, Zexun
Xu, Zhenlin
Gao, Cuiyun
Wang, Haiyan
Li, Jing
Gu, Zhaoquan
Zhang, Yanchun
contents Multimodal Large Language Models (MLLMs) may memorize sensitive cross-modal information during pretraining. However, existing MLLM unlearning benchmarks rely on synthetic knowledge injection or complete subject-level deletion, which fail to capture realistic, personalized deletion requests that require fine-grained factual control. In this paper, we introduce PPU-Bench, a real-world and fine-tuning-free benchmark for personalized partial unlearning in MLLMs. PPU-Bench contains 24K multimodal and unimodal samples derived from pre-existing knowledge of 500 public figures under three progressively challenging settings: Complete, Selective, and Personalized unlearning. The benchmark evaluates whether methods can remove target knowledge while preserving non-target facts, model utility, and cross-modal consistency. Extensive experiments show that Complete Unlearning often suppresses visual identity rather than factual knowledge, while Selective and Personalized Unlearning expose significant forget--retain trade-offs and challenges in intra-subject factual boundaries. Robustness analysis under cross-image and prompt-based attacks reveals distinct vulnerabilities across different unlearning settings. Motivated by these findings, we propose Boundary-Aware Optimization (BAO), which explicitly models intra-subject forget-retain boundaries. Experimental results on two representative methods demonstrate that BAO can effectively enforce intra-subject factual boundaries.
format Preprint
id arxiv_https___arxiv_org_abs_2605_08800
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PPU-Bench:Real World Benchmark for Personalized Partial Unlearning in Vision Language Models
Guang, Jiahui
Zhan, Zexun
Xu, Zhenlin
Gao, Cuiyun
Wang, Haiyan
Li, Jing
Gu, Zhaoquan
Zhang, Yanchun
Computer Vision and Pattern Recognition
Artificial Intelligence
Multimodal Large Language Models (MLLMs) may memorize sensitive cross-modal information during pretraining. However, existing MLLM unlearning benchmarks rely on synthetic knowledge injection or complete subject-level deletion, which fail to capture realistic, personalized deletion requests that require fine-grained factual control. In this paper, we introduce PPU-Bench, a real-world and fine-tuning-free benchmark for personalized partial unlearning in MLLMs. PPU-Bench contains 24K multimodal and unimodal samples derived from pre-existing knowledge of 500 public figures under three progressively challenging settings: Complete, Selective, and Personalized unlearning. The benchmark evaluates whether methods can remove target knowledge while preserving non-target facts, model utility, and cross-modal consistency. Extensive experiments show that Complete Unlearning often suppresses visual identity rather than factual knowledge, while Selective and Personalized Unlearning expose significant forget--retain trade-offs and challenges in intra-subject factual boundaries. Robustness analysis under cross-image and prompt-based attacks reveals distinct vulnerabilities across different unlearning settings. Motivated by these findings, we propose Boundary-Aware Optimization (BAO), which explicitly models intra-subject forget-retain boundaries. Experimental results on two representative methods demonstrate that BAO can effectively enforce intra-subject factual boundaries.
title PPU-Bench:Real World Benchmark for Personalized Partial Unlearning in Vision Language Models
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2605.08800