EmoAttack: Emotion-to-Image Diffusion Models for Emotional Backdoor Generation

• URL: http://arxiv.org/abs/2406.15863v2
• Date: Tue, 25 Mar 2025 16:08:20 GMT
• Title: EmoAttack: Emotion-to-Image Diffusion Models for Emotional Backdoor Generation
• Authors: Tianyu Wei, Shanmin Pang, Qi Guo, Yizhuo Ma, Xiaofeng Cao, Ming-Ming Cheng, Qing Guo,
• Abstract summary: We investigate a previously overlooked risk associated with text-to-image diffusion models, that is, utilizing emotion in the input texts to introduce negative content and provoke unfavorable emotions in users.<n>Specifically, we identify a new backdoor attack, i.e., emotion-aware backdoor attack (EmoAttack)<n>Unlike existing personalization methods, our approach fine-tunes a pre-trained diffusion model by establishing a mapping between a cluster of emotional words and a given reference image containing malicious negative content.
• Score: 48.95229349072138
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Text-to-image diffusion models can generate realistic images based on textual inputs, enabling users to convey their opinions visually through language. Meanwhile, within language, emotion plays a crucial role in expressing personal opinions in our daily lives and the inclusion of maliciously negative content can lead users astray, exacerbating negative emotions. Recognizing the success of diffusion models and the significance of emotion, we investigate a previously overlooked risk associated with text-to-image diffusion models, that is, utilizing emotion in the input texts to introduce negative content and provoke unfavorable emotions in users. Specifically, we identify a new backdoor attack, i.e., emotion-aware backdoor attack (EmoAttack), which introduces malicious negative content triggered by emotional texts during image generation. We formulate such an attack as a diffusion personalization problem to avoid extensive model retraining and propose the EmoBooth. Unlike existing personalization methods, our approach fine-tunes a pre-trained diffusion model by establishing a mapping between a cluster of emotional words and a given reference image containing malicious negative content. To validate the effectiveness of our method, we built a dataset and conducted extensive analysis and discussion about its effectiveness. Given consumers' widespread use of diffusion models, uncovering this threat is critical for society.

Related papers

• EmotiCrafter: Text-to-Emotional-Image Generation based on Valence-Arousal Model [23.26111054485357]
  We introduce the new task of continuous emotional image content generation (C-EICG) We present EmotiCrafter, an emotional image generation model that generates images based on text prompts and Valence-Arousal values.
  arXiv  Detail & Related papers  (2025-01-10T04:41:37Z)
• Emotional Images: Assessing Emotions in Images and Potential Biases in Generative Models [0.0]
  This paper examines potential biases and inconsistencies in emotional evocation of images produced by generative artificial intelligence (AI) models. We compare the emotions evoked by an AI-produced image to the emotions evoked by prompts used to create those images. Findings indicate that AI-generated images frequently lean toward negative emotional content, regardless of the original prompt.
  arXiv  Detail & Related papers  (2024-11-08T21:42:50Z)
• 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)
• EmoEdit: Evoking Emotions through Image Manipulation [62.416345095776656]
  Affective Image Manipulation (AIM) seeks to modify user-provided images to evoke specific emotional responses. We introduce EmoEdit, which extends AIM by incorporating content modifications to enhance emotional impact. Our method is evaluated both qualitatively and quantitatively, demonstrating superior performance compared to existing state-of-the-art techniques.
  arXiv  Detail & Related papers  (2024-05-21T10:18:45Z)
• Concept Arithmetics for Circumventing Concept Inhibition in Diffusion Models [58.065255696601604]
  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.
  arXiv  Detail & Related papers  (2024-04-21T16:35:16Z)
• Make Me Happier: Evoking Emotions Through Image Diffusion Models [36.40067582639123]
  We present a novel challenge of emotion-evoked image generation, aiming to synthesize images that evoke target emotions while retaining the semantics and structures of the original scenes. Due to the lack of emotion editing datasets, we provide a unique dataset consisting of 340,000 pairs of images and their emotion annotations.
  arXiv  Detail & Related papers  (2024-03-13T05:13:17Z)
• EmoTalker: Emotionally Editable Talking Face Generation via Diffusion Model [39.14430238946951]
  EmoTalker is an emotionally editable portraits animation approach based on the diffusion model. Emotion Intensity Block is introduced to analyze fine-grained emotions and strengths derived from prompts. Experiments show the effectiveness of EmoTalker in generating high-quality, emotionally customizable facial expressions.
  arXiv  Detail & Related papers  (2024-01-16T02:02:44Z)
• EmoGen: Emotional Image Content Generation with Text-to-Image Diffusion Models [11.901294654242376]
  We introduce Emotional Image Content Generation (EICG), a new task to generate semantic-clear and emotion-faithful images given emotion categories. Specifically, we propose an emotion space and construct a mapping network to align it with the powerful Contrastive Language-Image Pre-training (CLIP) space. Our method outperforms the state-of-the-art text-to-image approaches both quantitatively and qualitatively.
  arXiv  Detail & Related papers  (2024-01-09T15:23:21Z)
• Dynamic Causal Disentanglement Model for Dialogue Emotion Detection [77.96255121683011]
  We propose a Dynamic Causal Disentanglement Model based on hidden variable separation. This model effectively decomposes the content of dialogues and investigates the temporal accumulation of emotions. Specifically, we propose a dynamic temporal disentanglement model to infer the propagation of utterances and hidden variables.
  arXiv  Detail & Related papers  (2023-09-13T12:58:09Z)
• High-Level Context Representation for Emotion Recognition in Images [4.987022981158291]
  We propose an approach for high-level context representation extraction from images. The model relies on a single cue and a single encoding stream to correlate this representation with emotions. Our approach is more efficient than previous models and can be easily deployed to address real-world problems related to emotion recognition.
  arXiv  Detail & Related papers  (2023-05-05T13:20:41Z)
• Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models [103.61066310897928]
  Recent text-to-image generative models have demonstrated an unparalleled ability to generate diverse and creative imagery guided by a target text prompt. While revolutionary, current state-of-the-art diffusion models may still fail in generating images that fully convey the semantics in the given text prompt. We analyze the publicly available Stable Diffusion model and assess the existence of catastrophic neglect, where the model fails to generate one or more of the subjects from the input prompt. We introduce the concept of Generative Semantic Nursing (GSN), where we seek to intervene in the generative process on the fly during inference time to improve the faithfulness
  arXiv  Detail & Related papers  (2023-01-31T18:10:38Z)
• Language Does More Than Describe: On The Lack Of Figurative Speech in Text-To-Image Models [63.545146807810305]
  Text-to-image diffusion models can generate high-quality pictures from textual input prompts. These models have been trained using text data collected from content-based labelling protocols. We characterise the sentimentality, objectiveness and degree of abstraction of publicly available text data used to train current text-to-image diffusion models.
  arXiv  Detail & Related papers  (2022-10-19T14:20:05Z)
• Enhancing Cognitive Models of Emotions with Representation Learning [58.2386408470585]
  We present a novel deep learning-based framework to generate embedding representations of fine-grained emotions. Our framework integrates a contextualized embedding encoder with a multi-head probing model. Our model is evaluated on the Empathetic Dialogue dataset and shows the state-of-the-art result for classifying 32 emotions.
  arXiv  Detail & Related papers  (2021-04-20T16:55:15Z)
• Facial Expression Editing with Continuous Emotion Labels [76.36392210528105]
  Deep generative models have achieved impressive results in the field of automated facial expression editing. We propose a model that can be used to manipulate facial expressions in facial images according to continuous two-dimensional emotion labels.
  arXiv  Detail & Related papers  (2020-06-22T13:03:02Z)

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.