SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2405.19237 · 2024

ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron Pruning

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

While large-scale text-to-image diffusion models have demonstrated impressive image-generation capabilities, there are significant concerns about their potential misuse for generating unsafe content, violating copyright, and perpetuating societal biases. Recently, the text-to-image generation community has begun addressing these concerns by editing or unlearning undesired concepts from pre-trained models. However, these methods often involve data-intensive and inefficient fine-tuning or utilize various forms of token remapping, rendering them susceptible to adversarial jailbreaks. In this paper, we present a simple and effective training-free approach, ConceptPrune, wherein we first identify critical regions within pre-trained models responsible for generating undesirable concepts, thereby facilitating straightforward concept unlearning via weight pruning. Experiments across a range of concepts including artistic styles, nudity, object erasure, and gender debiasing demonstrate that target concepts can be efficiently erased by pruning a tiny fraction, approximately 0.12% of total weights, enabling multi-concept erasure and robustness against various white-box and black-box adversarial attacks.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2405.19237")
get_code_for_paper("2405.19237")
have("2405.19237")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2405.19237.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2405.19237.svg)](https://syntology.ai/paper/2405.19237)

Connect an agent — have() is free.