Saved in:
Bibliographic Details
Main Authors: Anilkumar, Vishnu Narayanan, Babu, Abhijith Sreesylesh, Vo, Trieu Hai, Kolla, Mohankrishna, Cuneo, Alexander
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.14185
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Generative multimodal models can exhibit safety failures that are inherently relational: two benign concepts can become unsafe when linked by a specific action or relation (e.g., child-drinking-wine). Existing unlearning and concept-erasure approaches often target isolated concepts or image-text pairs, which can cause collateral damage to benign uses of the same objects and relations. We propose relationship-aware safety unlearning: a framework that explicitly represents unsafe object-relation-object (O-R-O) tuples and applies targeted parameter-efficient edits (LoRA) to suppress unsafe tuples while preserving object marginals and safe neighboring relations. We include CLIP-based experiments and robustness evaluation under paraphrase, contextual, and out-of-distribution image attacks.