On the Feasibility of Poisoning Text-to-Image AI Models via Adversarial Mislabeling

• URL: http://arxiv.org/abs/2506.21874v1
• Date: Fri, 27 Jun 2025 03:13:47 GMT
• Title: On the Feasibility of Poisoning Text-to-Image AI Models via Adversarial Mislabeling
• Authors: Stanley Wu, Ronik Bhaskar, Anna Yoo Jeong Ha, Shawn Shan, Haitao Zheng, Ben Y. Zhao,
• Abstract summary: A text-to-image generative model is trained on millions of images sourced from the Internet, each paired with a detailed caption produced by Vision-Language Models (VLMs)<n>VLMs are vulnerable to stealthy adversarial attacks, where perturbations are added to images to mislead the VLMs into producing incorrect captions.<n>We find that while potential defenses can be effective, they can be targeted and circumvented by adaptive attackers.
• Score: 24.730395152276927
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Today's text-to-image generative models are trained on millions of images sourced from the Internet, each paired with a detailed caption produced by Vision-Language Models (VLMs). This part of the training pipeline is critical for supplying the models with large volumes of high-quality image-caption pairs during training. However, recent work suggests that VLMs are vulnerable to stealthy adversarial attacks, where adversarial perturbations are added to images to mislead the VLMs into producing incorrect captions. In this paper, we explore the feasibility of adversarial mislabeling attacks on VLMs as a mechanism to poisoning training pipelines for text-to-image models. Our experiments demonstrate that VLMs are highly vulnerable to adversarial perturbations, allowing attackers to produce benign-looking images that are consistently miscaptioned by the VLM models. This has the effect of injecting strong "dirty-label" poison samples into the training pipeline for text-to-image models, successfully altering their behavior with a small number of poisoned samples. We find that while potential defenses can be effective, they can be targeted and circumvented by adaptive attackers. This suggests a cat-and-mouse game that is likely to reduce the quality of training data and increase the cost of text-to-image model development. Finally, we demonstrate the real-world effectiveness of these attacks, achieving high attack success (over 73%) even in black-box scenarios against commercial VLMs (Google Vertex AI and Microsoft Azure).

Related papers

• AnyAttack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models [39.34959092321762]
  Vision-Language Models (VLMs) are vulnerable to image-based adversarial attacks.<n>We present AnyAttack, a self-supervised framework that transcends the limitations of conventional attacks.
  arXiv  Detail & Related papers  (2024-10-07T09:45:18Z)
• Downstream Transfer Attack: Adversarial Attacks on Downstream Models with Pre-trained Vision Transformers [95.22517830759193]
  This paper studies the transferability of such an adversarial vulnerability from a pre-trained ViT model to downstream tasks. We show that DTA achieves an average attack success rate (ASR) exceeding 90%, surpassing existing methods by a huge margin.
  arXiv  Detail & Related papers  (2024-08-03T08:07:03Z)
• MirrorCheck: Efficient Adversarial Defense for Vision-Language Models [55.73581212134293]
  We propose a novel, yet elegantly simple approach for detecting adversarial samples in Vision-Language Models. Our method leverages Text-to-Image (T2I) models to generate images based on captions produced by target VLMs. Empirical evaluations conducted on different datasets validate the efficacy of our approach.
  arXiv  Detail & Related papers  (2024-06-13T15:55:04Z)
• VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models [58.21452697997078]
  We propose a novel VQAttack model, which can generate both image and text perturbations with the designed modules. Experimental results on two VQA datasets with five validated models demonstrate the effectiveness of the proposed VQAttack.
  arXiv  Detail & Related papers  (2024-02-16T21:17:42Z)
• SA-Attack: Improving Adversarial Transferability of Vision-Language Pre-training Models via Self-Augmentation [56.622250514119294]
  In contrast to white-box adversarial attacks, transfer attacks are more reflective of real-world scenarios. We propose a self-augment-based transfer attack method, termed SA-Attack.
  arXiv  Detail & Related papers  (2023-12-08T09:08:50Z)
• InstructTA: Instruction-Tuned Targeted Attack for Large Vision-Language Models [13.21813503235793]
  Large vision-language models (LVLMs) have demonstrated their incredible capability in image understanding and response generation. In this paper, we formulate a novel and practical targeted attack scenario that the adversary can only know the vision encoder of the victim LVLM. We propose an instruction-tuned targeted attack (dubbed textscInstructTA) to deliver the targeted adversarial attack on LVLMs with high transferability.
  arXiv  Detail & Related papers  (2023-12-04T13:40:05Z)
• Adversarial Prompt Tuning for Vision-Language Models [86.5543597406173]
  Adversarial Prompt Tuning (AdvPT) is a technique to enhance the adversarial robustness of image encoders in Vision-Language Models (VLMs) We demonstrate that AdvPT improves resistance against white-box and black-box adversarial attacks and exhibits a synergistic effect when combined with existing image-processing-based defense techniques.
  arXiv  Detail & Related papers  (2023-11-19T07:47:43Z)
• VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models [46.14455492739906]
  Vision-Language (VL) pre-trained models have shown their superiority on many multimodal tasks. Existing approaches mainly focus on exploring the adversarial robustness under the white-box setting. We propose VLATTACK to generate adversarial samples by fusing perturbations of images and texts from both single-modal and multimodal levels.
  arXiv  Detail & Related papers  (2023-10-07T02:18:52Z)
• Image Hijacks: Adversarial Images can Control Generative Models at Runtime [8.603201325413192]
  We discover image hijacks, adversarial images that control the behaviour of vision-language models at inference time. We derive the Prompt Matching method, allowing us to train hijacks matching the behaviour of an arbitrary user-defined text prompt. We use Behaviour Matching to craft hijacks for four types of attack, forcing VLMs to generate outputs of the adversary's choice, leak information from their context window, override their safety training, and believe false statements.
  arXiv  Detail & Related papers  (2023-09-01T03:53:40Z)
• Learning to Attack: Towards Textual Adversarial Attacking in Real-world Situations [81.82518920087175]
  Adversarial attacking aims to fool deep neural networks with adversarial examples. We propose a reinforcement learning based attack model, which can learn from attack history and launch attacks more efficiently.
  arXiv  Detail & Related papers  (2020-09-19T09:12:24Z)

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.