Intriguing Properties of Diffusion Models: An Empirical Study of the Natural Attack Capability in Text-to-Image Generative Models

• URL: http://arxiv.org/abs/2308.15692v2
• Date: Thu, 2 May 2024 01:12:48 GMT
• Title: Intriguing Properties of Diffusion Models: An Empirical Study of the Natural Attack Capability in Text-to-Image Generative Models
• Authors: Takami Sato, Justin Yue, Nanze Chen, Ningfei Wang, Qi Alfred Chen,
• Abstract summary: We find that state-of-the-art deep neural network (DNN) models still hold their prediction even if we intentionally remove their robust features. The NDD attack shows a significantly high capability to generate low-cost, model-agnostic, and transferable adversarial attacks.
• Score: 22.675911411028633
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Denoising probabilistic diffusion models have shown breakthrough performance to generate more photo-realistic images or human-level illustrations than the prior models such as GANs. This high image-generation capability has stimulated the creation of many downstream applications in various areas. However, we find that this technology is actually a double-edged sword: We identify a new type of attack, called the Natural Denoising Diffusion (NDD) attack based on the finding that state-of-the-art deep neural network (DNN) models still hold their prediction even if we intentionally remove their robust features, which are essential to the human visual system (HVS), through text prompts. The NDD attack shows a significantly high capability to generate low-cost, model-agnostic, and transferable adversarial attacks by exploiting the natural attack capability in diffusion models. To systematically evaluate the risk of the NDD attack, we perform a large-scale empirical study with our newly created dataset, the Natural Denoising Diffusion Attack (NDDA) dataset. We evaluate the natural attack capability by answering 6 research questions. Through a user study, we find that it can achieve an 88% detection rate while being stealthy to 93% of human subjects; we also find that the non-robust features embedded by diffusion models contribute to the natural attack capability. To confirm the model-agnostic and transferable attack capability, we perform the NDD attack against the Tesla Model 3 and find that 73% of the physically printed attacks can be detected as stop signs. Our hope is that the study and dataset can help our community be aware of the risks in diffusion models and facilitate further research toward robust DNN models.

Related papers

• Watch the Watcher! Backdoor Attacks on Security-Enhancing Diffusion Models [65.30406788716104]
  This work investigates the vulnerabilities of security-enhancing diffusion models. We demonstrate that these models are highly susceptible to DIFF2, a simple yet effective backdoor attack. Case studies show that DIFF2 can significantly reduce both post-purification and certified accuracy across benchmark datasets and models.
  arXiv  Detail & Related papers  (2024-06-14T02:39:43Z)
• Adv-Diffusion: Imperceptible Adversarial Face Identity Attack via Latent Diffusion Model [61.53213964333474]
  We propose a unified framework Adv-Diffusion that can generate imperceptible adversarial identity perturbations in the latent space but not the raw pixel space. Specifically, we propose the identity-sensitive conditioned diffusion generative model to generate semantic perturbations in the surroundings. The designed adaptive strength-based adversarial perturbation algorithm can ensure both attack transferability and stealthiness.
  arXiv  Detail & Related papers  (2023-12-18T15:25:23Z)
• Leveraging Diffusion-Based Image Variations for Robust Training on Poisoned Data [26.551317580666353]
  Backdoor attacks pose a serious security threat for training neural networks. We propose a novel approach that enables model training on potentially poisoned datasets by utilizing the power of recent diffusion models.
  arXiv  Detail & Related papers  (2023-10-10T07:25:06Z)
• MedDiffusion: Boosting Health Risk Prediction via Diffusion-based Data Augmentation [58.93221876843639]
  This paper introduces a novel, end-to-end diffusion-based risk prediction model, named MedDiffusion. It enhances risk prediction performance by creating synthetic patient data during training to enlarge sample space. It discerns hidden relationships between patient visits using a step-wise attention mechanism, enabling the model to automatically retain the most vital information for generating high-quality data.
  arXiv  Detail & Related papers  (2023-10-04T01:36:30Z)
• Data Forensics in Diffusion Models: A Systematic Analysis of Membership Privacy [62.16582309504159]
  We develop a systematic analysis of membership inference attacks on diffusion models and propose novel attack methods tailored to each attack scenario. Our approach exploits easily obtainable quantities and is highly effective, achieving near-perfect attack performance (>0.9 AUCROC) in realistic scenarios.
  arXiv  Detail & Related papers  (2023-02-15T17:37:49Z)
• Exploiting epistemic uncertainty of the deep learning models to generate adversarial samples [0.7734726150561088]
  "Adversarial Machine Learning" aims to devise new adversarial attacks and to defend against these attacks with more robust architectures. This study explores the usage of quantified epistemic uncertainty obtained from Monte-Carlo Dropout Sampling for adversarial attack purposes. Our results show that our proposed hybrid attack approach increases the attack success rates from 82.59% to 85.40%, 82.86% to 89.92% and 88.06% to 90.03% on datasets.
  arXiv  Detail & Related papers  (2021-02-08T11:59:27Z)
• Model Extraction Attacks on Graph Neural Networks: Taxonomy and Realization [40.37373934201329]
  We investigate and develop model extraction attacks against GNN models. We first formalise the threat modelling in the context of GNN model extraction. We then present detailed methods which utilise the accessible knowledge in each threat to implement the attacks.
  arXiv  Detail & Related papers  (2020-10-24T03:09:37Z)
• Adversarial Exposure Attack on Diabetic Retinopathy Imagery Grading [75.73437831338907]
  Diabetic Retinopathy (DR) is a leading cause of vision loss around the world. To help diagnose it, numerous cutting-edge works have built powerful deep neural networks (DNNs) to automatically grade DR via retinal fundus images (RFIs) RFIs are commonly affected by camera exposure issues that may lead to incorrect grades. In this paper, we study this problem from the viewpoint of adversarial attacks.
  arXiv  Detail & Related papers  (2020-09-19T13:47:33Z)
• 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.