Concept Arithmetics for Circumventing Concept Inhibition in Diffusion Models

• URL: http://arxiv.org/abs/2404.13706v1
• Date: Sun, 21 Apr 2024 16:35:16 GMT
• Title: Concept Arithmetics for Circumventing Concept Inhibition in Diffusion Models
• Authors: Vitali Petsiuk, Kate Saenko,
• Abstract summary: We use compositional property of diffusion models, which allows to leverage multiple prompts in a single image generation. We argue that it is essential to consider all possible approaches to image generation with diffusion models that can be employed by an adversary.
• Score: 58.065255696601604
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Motivated by ethical and legal concerns, the scientific community is actively developing methods to limit the misuse of Text-to-Image diffusion models for reproducing copyrighted, violent, explicit, or personal information in the generated images. Simultaneously, researchers put these newly developed safety measures to the test by assuming the role of an adversary to find vulnerabilities and backdoors in them. We use compositional property of diffusion models, which allows to leverage multiple prompts in a single image generation. This property allows us to combine other concepts, that should not have been affected by the inhibition, to reconstruct the vector, responsible for target concept generation, even though the direct computation of this vector is no longer accessible. We provide theoretical and empirical evidence why the proposed attacks are possible and discuss the implications of these findings for safe model deployment. We argue that it is essential to consider all possible approaches to image generation with diffusion models that can be employed by an adversary. Our work opens up the discussion about the implications of concept arithmetics and compositional inference for safety mechanisms in diffusion models. Content Advisory: This paper contains discussions and model-generated content that may be considered offensive. Reader discretion is advised. Project page: https://cs-people.bu.edu/vpetsiuk/arc

Related papers

• Safety Without Semantic Disruptions: Editing-free Safe Image Generation via Context-preserving Dual Latent Reconstruction [49.60774626839712]
  Training multimodal generative models can expose users to harmful, unsafe and controversial or culturally-inappropriate outputs. We propose a modular, dynamic solution that leverages safety-context embeddings and a dual reconstruction process to generate safer images. We achieve state-of-the-art results on safe image generation benchmarks, while offering controllable variation of model safety.
  arXiv  Detail & Related papers  (2024-11-21T09:47:13Z)
• Safeguard Text-to-Image Diffusion Models with Human Feedback Inversion [51.931083971448885]
  We propose a framework named Human Feedback Inversion (HFI), where human feedback on model-generated images is condensed into textual tokens guiding the mitigation or removal of problematic images. Our experimental results demonstrate our framework significantly reduces objectionable content generation while preserving image quality, contributing to the ethical deployment of AI in the public sphere.
  arXiv  Detail & Related papers  (2024-07-17T05:21:41Z)
• Deceptive Diffusion: Generating Synthetic Adversarial Examples [2.7309692684728617]
  We introduce the concept of deceptive diffusion -- training a generative AI model to produce adversarial images. A traditional adversarial attack algorithm aims to perturb an existing image to induce a misclassificaton. The deceptive diffusion model can create an arbitrary number of new, misclassified images that are not directly associated with training or test images.
  arXiv  Detail & Related papers  (2024-06-28T10:30:46Z)
• Six-CD: Benchmarking Concept Removals for Benign Text-to-image Diffusion Models [58.74606272936636]
  Text-to-image (T2I) diffusion models have shown exceptional capabilities in generating images that closely correspond to textual prompts. The models could be exploited for malicious purposes, such as generating images with violence or nudity, or creating unauthorized portraits of public figures in inappropriate contexts. concept removal methods have been proposed to modify diffusion models to prevent the generation of malicious and unwanted concepts.
  arXiv  Detail & Related papers  (2024-06-21T03:58:44Z)
• Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation [36.93643249463899]
  A risk with diffusion-based models is the potential generation of inappropriate content, such as biased or harmful images. Previous work interprets vectors in an interpretable latent space of diffusion models as semantic concepts. We propose a novel self-supervised approach to find interpretable latent directions for a given concept.
  arXiv  Detail & Related papers  (2023-11-28T20:40:45Z)
• Ring-A-Bell! How Reliable are Concept Removal Methods for Diffusion Models? [52.238883592674696]
  Ring-A-Bell is a model-agnostic red-teaming tool for T2I diffusion models. It identifies problematic prompts for diffusion models with the corresponding generation of inappropriate content. Our results show that Ring-A-Bell, by manipulating safe prompting benchmarks, can transform prompts that were originally regarded as safe to evade existing safety mechanisms.
  arXiv  Detail & Related papers  (2023-10-16T02:11:20Z)
• Ablating Concepts in Text-to-Image Diffusion Models [57.9371041022838]
  Large-scale text-to-image diffusion models can generate high-fidelity images with powerful compositional ability. These models are typically trained on an enormous amount of Internet data, often containing copyrighted material, licensed images, and personal photos. We propose an efficient method of ablating concepts in the pretrained model, preventing the generation of a target concept.
  arXiv  Detail & Related papers  (2023-03-23T17:59:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.