Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models

• URL: http://arxiv.org/abs/2310.13828v3
• Date: Mon, 29 Apr 2024 17:23:59 GMT
• Title: Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models
• Authors: Shawn Shan, Wenxin Ding, Josephine Passananti, Stanley Wu, Haitao Zheng, Ben Y. Zhao,
• Abstract summary: We show that poisoning attacks can be successful on generative models. We introduce Nightshade, an optimized prompt-specific poisoning attack. We show that Nightshade attacks can destabilize general features in a text-to-image generative model.
• Score: 26.301156075883483
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Data poisoning attacks manipulate training data to introduce unexpected behaviors into machine learning models at training time. For text-to-image generative models with massive training datasets, current understanding of poisoning attacks suggests that a successful attack would require injecting millions of poison samples into their training pipeline. In this paper, we show that poisoning attacks can be successful on generative models. We observe that training data per concept can be quite limited in these models, making them vulnerable to prompt-specific poisoning attacks, which target a model's ability to respond to individual prompts. We introduce Nightshade, an optimized prompt-specific poisoning attack where poison samples look visually identical to benign images with matching text prompts. Nightshade poison samples are also optimized for potency and can corrupt an Stable Diffusion SDXL prompt in <100 poison samples. Nightshade poison effects "bleed through" to related concepts, and multiple attacks can composed together in a single prompt. Surprisingly, we show that a moderate number of Nightshade attacks can destabilize general features in a text-to-image generative model, effectively disabling its ability to generate meaningful images. Finally, we propose the use of Nightshade and similar tools as a last defense for content creators against web scrapers that ignore opt-out/do-not-crawl directives, and discuss possible implications for model trainers and content creators.

Related papers

• The Victim and The Beneficiary: Exploiting a Poisoned Model to Train a Clean Model on Poisoned Data [4.9676716806872125]
  backdoor attacks have posed a serious security threat to the training process of deep neural networks (DNNs) We propose a novel dual-network training framework: The Victim and The Beneficiary (V&B), which exploits a poisoned model to train a clean model without extra benign samples. Our framework is effective in preventing backdoor injection and robust to various attacks while maintaining the performance on benign samples.
  arXiv  Detail & Related papers  (2024-04-17T11:15:58Z)
• Exploring Model Dynamics for Accumulative Poisoning Discovery [62.08553134316483]
  We propose a novel information measure, namely, Memorization Discrepancy, to explore the defense via the model-level information. By implicitly transferring the changes in the data manipulation to that in the model outputs, Memorization Discrepancy can discover the imperceptible poison samples. We thoroughly explore its properties and propose Discrepancy-aware Sample Correction (DSC) to defend against accumulative poisoning attacks.
  arXiv  Detail & Related papers  (2023-06-06T14:45:24Z)
• Adversarial Examples Make Strong Poisons [55.63469396785909]
  We show that adversarial examples, originally intended for attacking pre-trained models, are even more effective for data poisoning than recent methods designed specifically for poisoning. Our method, adversarial poisoning, is substantially more effective than existing poisoning methods for secure dataset release.
  arXiv  Detail & Related papers  (2021-06-21T01:57:14Z)
• Accumulative Poisoning Attacks on Real-time Data [56.96241557830253]
  We show that a well-designed but straightforward attacking strategy can dramatically amplify the poisoning effects. Our work validates that a well-designed but straightforward attacking strategy can dramatically amplify the poisoning effects.
  arXiv  Detail & Related papers  (2021-06-18T08:29:53Z)
• De-Pois: An Attack-Agnostic Defense against Data Poisoning Attacks [17.646155241759743]
  De-Pois is an attack-agnostic defense against poisoning attacks. We implement four types of poisoning attacks and evaluate De-Pois with five typical defense methods.
  arXiv  Detail & Related papers  (2021-05-08T04:47:37Z)
• What Doesn't Kill You Makes You Robust(er): Adversarial Training against Poisons and Backdoors [57.040948169155925]
  We extend the adversarial training framework to defend against (training-time) poisoning and backdoor attacks. Our method desensitizes networks to the effects of poisoning by creating poisons during training and injecting them into training batches. We show that this defense withstands adaptive attacks, generalizes to diverse threat models, and incurs a better performance trade-off than previous defenses.
  arXiv  Detail & Related papers  (2021-02-26T17:54:36Z)
• DeepPoison: Feature Transfer Based Stealthy Poisoning Attack [2.1445455835823624]
  DeepPoison is a novel adversarial network of one generator and two discriminators. DeepPoison can achieve a state-of-the-art attack success rate, as high as 91.74%.
  arXiv  Detail & Related papers  (2021-01-06T15:45:36Z)
• Concealed Data Poisoning Attacks on NLP Models [56.794857982509455]
  Adversarial attacks alter NLP model predictions by perturbing test-time inputs. We develop a new data poisoning attack that allows an adversary to control model predictions whenever a desired trigger phrase is present in the input.
  arXiv  Detail & Related papers  (2020-10-23T17:47:06Z)
• Poison Attacks against Text Datasets with Conditional Adversarially Regularized Autoencoder [78.01180944665089]
  This paper demonstrates a fatal vulnerability in natural language inference (NLI) and text classification systems. We present a 'backdoor poisoning' attack on NLP models.
  arXiv  Detail & Related papers  (2020-10-06T13:03:49Z)
• Bullseye Polytope: A Scalable Clean-Label Poisoning Attack with Improved Transferability [23.031305862548226]
  A recent source of concern for neural networks is the emergence of clean-label dataset poisoning attacks. We propose a scalable and transferable clean-label poisoning attack against transfer learning. Our attack, Bullseye Polytope, improves the attack success rate of the current state-of-the-art by 26.75% in end-to-end transfer learning.
  arXiv  Detail & Related papers  (2020-05-01T03:22:36Z)

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.