CogMorph: Cognitive Morphing Attacks for Text-to-Image Models

• URL: http://arxiv.org/abs/2501.11815v2
• Date: Wed, 22 Jan 2025 03:17:01 GMT
• Title: CogMorph: Cognitive Morphing Attacks for Text-to-Image Models
• Authors: Zonglei Jing, Zonghao Ying, Le Wang, Siyuan Liang, Aishan Liu, Xianglong Liu, Dacheng Tao,
• Abstract summary: This paper reveals a significant and previously unrecognized ethical risk inherent in text-to-image (T2I) generative models. We introduce a novel method, termed the Cognitive Morphing Attack (CogMorph), which manipulates T2I models to generate images that retain the original core subjects but embeds toxic or harmful contextual elements.
• Score: 65.38747950692752
• License:
• Abstract: The development of text-to-image (T2I) generative models, that enable the creation of high-quality synthetic images from textual prompts, has opened new frontiers in creative design and content generation. However, this paper reveals a significant and previously unrecognized ethical risk inherent in this technology and introduces a novel method, termed the Cognitive Morphing Attack (CogMorph), which manipulates T2I models to generate images that retain the original core subjects but embeds toxic or harmful contextual elements. This nuanced manipulation exploits the cognitive principle that human perception of concepts is shaped by the entire visual scene and its context, producing images that amplify emotional harm far beyond attacks that merely preserve the original semantics. To address this, we first construct an imagery toxicity taxonomy spanning 10 major and 48 sub-categories, aligned with human cognitive-perceptual dimensions, and further build a toxicity risk matrix resulting in 1,176 high-quality T2I toxic prompts. Based on this, our CogMorph first introduces Cognitive Toxicity Augmentation, which develops a cognitive toxicity knowledge base with rich external toxic representations for humans (e.g., fine-grained visual features) that can be utilized to further guide the optimization of adversarial prompts. In addition, we present Contextual Hierarchical Morphing, which hierarchically extracts critical parts of the original prompt (e.g., scenes, subjects, and body parts), and then iteratively retrieves and fuses toxic features to inject harmful contexts. Extensive experiments on multiple open-sourced T2I models and black-box commercial APIs (e.g., DALLE-3) demonstrate the efficacy of CogMorph which significantly outperforms other baselines by large margins (+20.62% on average).

Related papers

• Just KIDDIN: Knowledge Infusion and Distillation for Detection of INdecent Memes [8.337745035712311]
  We propose a novel framework that integrates Knowledge Distillation (KD) from Large Visual Language Models (LVLMs) and knowledge infusion to enhance the performance of toxicity detection in hateful memes. Our approach extracts sub-knowledge graphs from ConceptNet, a large-scale commonsense Knowledge Graph (KG) to be infused within a compact VLM framework. Experimental results from our study on two hate speech benchmark datasets demonstrate superior performance over the state-of-the-art baselines.
  arXiv  Detail & Related papers  (2024-11-19T02:39:28Z)
• Safe Text-to-Image Generation: Simply Sanitize the Prompt Embedding [13.481343482138888]
  We propose a vision-agnostic safe generation framework, Embedding Sanitizer (ES) ES focuses on erasing inappropriate concepts from prompt embeddings and uses the sanitized embeddings to guide the model for safe generation. ES significantly outperforms existing safeguards in terms of interpretability and controllability while maintaining generation quality.
  arXiv  Detail & Related papers  (2024-11-15T16:29:02Z)
• 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)
• SafeGen: Mitigating Sexually Explicit Content Generation in Text-to-Image Models [28.23494821842336]
  Text-to-image models may be tricked into generating not-safe-for-work (NSFW) content. We present SafeGen, a framework to mitigate sexual content generation by text-to-image models.
  arXiv  Detail & Related papers  (2024-04-10T00:26:08Z)
• Evaluating Text-to-Image Generative Models: An Empirical Study on Human Image Synthesis [21.619269792415903]
  We present an empirical study introducing a nuanced evaluation framework for text-to-image (T2I) generative models. Our framework categorizes evaluations into two distinct groups: first, focusing on image qualities such as aesthetics and realism, and second, examining text conditions through concept coverage and fairness.
  arXiv  Detail & Related papers  (2024-03-08T07:41:47Z)
• ToViLaG: Your Visual-Language Generative Model is Also An Evildoer [36.60526586838288]
  Recent large-scale Visual-Language Generative Models (VLGMs) have achieved unprecedented improvement in multimodal image/text generation. These models might also generate toxic content, e.g., offensive text and pornography images, raising significant ethical risks. This work delves into the propensity for toxicity generation and susceptibility to toxic data across various VLGMs.
  arXiv  Detail & Related papers  (2023-12-13T08:25:07Z)
• DreamCreature: Crafting Photorealistic Virtual Creatures from Imagination [140.1641573781066]
  We introduce a novel task, Virtual Creatures Generation: Given a set of unlabeled images of the target concepts, we aim to train a T2I model capable of creating new, hybrid concepts. We propose a new method called DreamCreature, which identifies and extracts the underlying sub-concepts. The T2I thus adapts to generate novel concepts with faithful structures and photorealistic appearance.
  arXiv  Detail & Related papers  (2023-11-27T01:24:31Z)
• Parents and Children: Distinguishing Multimodal DeepFakes from Natural Images [60.34381768479834]
  Recent advancements in diffusion models have enabled the generation of realistic deepfakes from textual prompts in natural language. We pioneer a systematic study on deepfake detection generated by state-of-the-art diffusion models.
  arXiv  Detail & Related papers  (2023-04-02T10:25:09Z)
• Constructing Highly Inductive Contexts for Dialogue Safety through Controllable Reverse Generation [65.48908724440047]
  We propose a method called emphreverse generation to construct adversarial contexts conditioned on a given response. We test three popular pretrained dialogue models (Blender, DialoGPT, and Plato2) and find that BAD+ can largely expose their safety problems.
  arXiv  Detail & Related papers  (2022-12-04T12:23:41Z)
• Aggregated Contextual Transformations for High-Resolution Image Inpainting [57.241749273816374]
  We propose an enhanced GAN-based model, named Aggregated COntextual-Transformation GAN (AOT-GAN) for high-resolution image inpainting. To enhance context reasoning, we construct the generator of AOT-GAN by stacking multiple layers of a proposed AOT block. For improving texture synthesis, we enhance the discriminator of AOT-GAN by training it with a tailored mask-prediction task.
  arXiv  Detail & Related papers  (2021-04-03T15:50:17Z)

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.