Harm Amplification in Text-to-Image Models

• URL: http://arxiv.org/abs/2402.01787v2
• Date: Fri, 17 May 2024 19:36:55 GMT
• Title: Harm Amplification in Text-to-Image Models
• Authors: Susan Hao, Renee Shelby, Yuchi Liu, Hansa Srinivasan, Mukul Bhutani, Burcu Karagol Ayan, Ryan Poplin, Shivani Poddar, Sarah Laszlo,
• Abstract summary: Text-to-image (T2I) models have emerged as a significant advancement in generative AI. There exist safety concerns regarding their potential to produce harmful image outputs even when users input seemingly safe prompts. This phenomenon, where T2I models generate harmful representations that were not explicit in the input, poses a potentially greater risk than adversarial prompts.
• Score: 5.397559484007124
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Text-to-image (T2I) models have emerged as a significant advancement in generative AI; however, there exist safety concerns regarding their potential to produce harmful image outputs even when users input seemingly safe prompts. This phenomenon, where T2I models generate harmful representations that were not explicit in the input, poses a potentially greater risk than adversarial prompts, leaving users unintentionally exposed to harms. Our paper addresses this issue by formalizing a definition for this phenomenon which we term harm amplification. We further contribute to the field by developing a framework of methodologies to quantify harm amplification in which we consider the harm of the model output in the context of user input. We then empirically examine how to apply these different methodologies to simulate real-world deployment scenarios including a quantification of disparate impacts across genders resulting from harm amplification. Together, our work aims to offer researchers tools to comprehensively address safety challenges in T2I systems and contribute to the responsible deployment of generative AI models.

Related papers

• Direct Unlearning Optimization for Robust and Safe Text-to-Image Models [29.866192834825572]
  Unlearning techniques have been developed to remove the model's ability to generate potentially harmful content. These methods are easily bypassed by adversarial attacks, making them unreliable for ensuring the safety of generated images. We propose Direct Unlearning Optimization (DUO), a novel framework for removing Not Safe For Work (NSFW) content from T2I models.
  arXiv  Detail & Related papers  (2024-07-17T08:19:11Z)
• Six-CD: Benchmarking Concept Removals for Benign Text-to-image Diffusion Models [58.74606272936636]
  Text-to-image (T2I) diffusion models have shown exceptional capabilities in generating images that closely correspond to textual prompts. The models could be exploited for malicious purposes, such as generating images with violence or nudity, or creating unauthorized portraits of public figures in inappropriate contexts. concept removal methods have been proposed to modify diffusion models to prevent the generation of malicious and unwanted concepts.
  arXiv  Detail & Related papers  (2024-06-21T03:58:44Z)
• 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)
• Humanizing Machine-Generated Content: Evading AI-Text Detection through Adversarial Attack [24.954755569786396]
  We propose a framework for a broader class of adversarial attacks, designed to perform minor perturbations in machine-generated content to evade detection. We consider two attack settings: white-box and black-box, and employ adversarial learning in dynamic scenarios to assess the potential enhancement of the current detection model's robustness. The empirical results reveal that the current detection models can be compromised in as little as 10 seconds, leading to the misclassification of machine-generated text as human-written content.
  arXiv  Detail & Related papers  (2024-04-02T12:49:22Z)
• Adversarial Nibbler: An Open Red-Teaming Method for Identifying Diverse Harms in Text-to-Image Generation [19.06501699814924]
  We build the Adversarial Nibbler Challenge, a red-teaming methodology for crowdsourcing implicitly adversarial prompts. The challenge is run in consecutive rounds to enable a sustained discovery and analysis of safety pitfalls in T2I models. We find that 14% of images that humans consider harmful are mislabeled as safe'' by machines.
  arXiv  Detail & Related papers  (2024-02-14T22:21:12Z)
• Analyzing Adversarial Inputs in Deep Reinforcement Learning [53.3760591018817]
  We present a comprehensive analysis of the characterization of adversarial inputs, through the lens of formal verification. We introduce a novel metric, the Adversarial Rate, to classify models based on their susceptibility to such perturbations. Our analysis empirically demonstrates how adversarial inputs can affect the safety of a given DRL system with respect to such perturbations.
  arXiv  Detail & Related papers  (2024-02-07T21:58:40Z)
• Navigating the OverKill in Large Language Models [84.62340510027042]
  We investigate the factors for overkill by exploring how models handle and determine the safety of queries. Our findings reveal the presence of shortcuts within models, leading to an over-attention of harmful words like 'kill' and prompts emphasizing safety will exacerbate overkill. We introduce Self-Contrastive Decoding (Self-CD), a training-free and model-agnostic strategy, to alleviate this phenomenon.
  arXiv  Detail & Related papers  (2024-01-31T07:26:47Z)
• Fortifying Ethical Boundaries in AI: Advanced Strategies for Enhancing Security in Large Language Models [3.9490749767170636]
  Large language models (LLMs) have revolutionized text generation, translation, and question-answering tasks. Despite their widespread use, LLMs present challenges such as ethical dilemmas when models are compelled to respond inappropriately. This paper addresses these challenges by introducing a multi-pronged approach that includes: 1) filtering sensitive vocabulary from user input to prevent unethical responses; 2) detecting role-playing to halt interactions that could lead to 'prison break' scenarios; and 4) extending these methodologies to various LLM derivatives like Multi-Model Large Language Models (MLLMs)
  arXiv  Detail & Related papers  (2024-01-27T08:09:33Z)
• Ring-A-Bell! How Reliable are Concept Removal Methods for Diffusion Models? [52.238883592674696]
  Ring-A-Bell is a model-agnostic red-teaming tool for T2I diffusion models. It identifies problematic prompts for diffusion models with the corresponding generation of inappropriate content. Our results show that Ring-A-Bell, by manipulating safe prompting benchmarks, can transform prompts that were originally regarded as safe to evade existing safety mechanisms.
  arXiv  Detail & Related papers  (2023-10-16T02:11:20Z)
• Adversarial Nibbler: A Data-Centric Challenge for Improving the Safety of Text-to-Image Models [6.475537049815622]
  Adversarial Nibbler is a data-centric challenge, part of the DataPerf challenge suite, organized and supported by Kaggle and MLCommons.
  arXiv  Detail & Related papers  (2023-05-22T15:02:40Z)
• Overcoming Failures of Imagination in AI Infused System Development and Deployment [71.9309995623067]
  NeurIPS 2020 requested that research paper submissions include impact statements on "potential nefarious uses and the consequences of failure" We argue that frameworks of harms must be context-aware and consider a wider range of potential stakeholders, system affordances, as well as viable proxies for assessing harms in the widest sense.
  arXiv  Detail & Related papers  (2020-11-26T18:09:52Z)

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.