A Concept is More Than a Word: Diversified Unlearning in Text-to-Image Diffusion Models

TL;DR

This paper introduces Diversified Unlearning, a novel framework for more precise and robust concept removal in text-to-image diffusion models by using diverse prompts instead of keywords, improving safety and reliability.

Contribution

It proposes a distributional approach to concept unlearning that overcomes keyword limitations, enhancing erasure accuracy and robustness in diffusion models.

Findings

Outperforms existing methods in concept erasure accuracy

Maintains better retention of unrelated concepts

Shows increased robustness against adversarial recovery attacks

Abstract

Concept unlearning has emerged as a promising direction for reducing the risks of harmful content generation in text-to-image diffusion models by selectively erasing undesirable concepts from a model's parameters. Existing approaches typically rely on keywords to identify the target concept to be unlearned. However, we show that this keyword-based formulation is inherently limited: a visual concept is multi-dimensional, can be expressed in diverse textual forms, and often overlap with related concepts in the latent space, making keyword-only unlearning, which imprecisely indicate the target concept is brittle and prone to over-forgetting. This occurs because a single keyword represents only a narrow point estimate of the concept, failing to cover its full semantic distribution and entangled variations in the latent space. To address this limitation, we propose Diversified Unlearning, a distributional framework that represents a concept through a set of contextually diverse prompts rather than a single keyword. This richer representation enables more precise and robust unlearning. Through extensive experiments across multiple benchmarks and state-of-the-art baselines, we demonstrate that integrating Diversified Unlearning as an add-on component into existing unlearning pipelines consistently achieves stronger erasure, better retention of unrelated concepts, and improved robustness against adversarial recovery attacks.