Do Concept Replacement Techniques Really Erase Unacceptable Concepts?
Generative models, particularly diffusion-based text-to-image (T2I) models, have demonstrated astounding success. However, aligning them to avoid generating content with unacceptable concepts (e.g., offensive or copyrighted content, or celebrity likenesses) remains a significant challenge. Concept replacement techniques (CRTs) aim to address this challenge, often by trying to "erase" unacceptable concepts from models. Recently, model providers have started offering image editing services which accept an image and a text prompt as input, to produce an image altered as specified by the prompt. These are known as image-to-image (I2I) models. In this paper, we first use an I2I model to empirically demonstrate that today's state-of-the-art CRTs do not in fact erase unacceptable concepts. Existing CRTs are thus likely to be ineffective in emerging I2I scenarios, despite their proven ability to remove unwanted concepts in T2I pipelines, highlighting the need to understand this discrepancy between T2I and I2I settings. Next, we argue that a good CRT, while replacing unacceptable concepts, should preserve other concepts specified in the inputs to generative models. We call this fidelity. Prior work on CRTs have neglected fidelity in the case of unacceptable concepts. Finally, we propose the use of targeted image-editing techniques to achieve both effectiveness and fidelity. We present such a technique, AntiMirror, and demonstrate its viability.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Espresso: Robust Concept Filtering in Text-to-Image Models
Diffusion based text-to-image models are trained on large datasets scraped from the Internet, potentially containing unacceptable concepts (e.g., copyright-infringing or unsafe). We need concept removal techniques (CRTs)…
Memories of Forgotten Concepts
Diffusion models dominate the space of text-to-image generation, yet they may produce undesirable outputs, including explicit content or private data. To mitigate this, concept ablation techniques have been explored to l…
Image GenerationText to Image GenerationText-to-Image GenerationDoes Representation Intervention Really Identify Desired Concepts and Elicit Alignment?
Representation intervention aims to locate and modify the representations that encode the underlying concepts in Large Language Models (LLMs) to elicit the aligned and expected behaviors. Despite the empirical success, i…
Code GenerationMathSafety AlignmentErased or Dormant? Rethinking Concept Erasure Through Reversibility
To what extent does concept erasure eliminate generative capacity in diffusion models? While prior evaluations have primarily focused on measuring concept suppression under specific textual prompts, we explore a compleme…
When Are Concepts Erased From Diffusion Models?
Concept erasure, the ability to selectively prevent a model from generating specific concepts, has attracted growing interest, with various approaches emerging to address the challenge. However, it remains unclear how th…