Evidencing Unauthorized Training Data from AI Generated Content using Information Isotopes

• URL: http://arxiv.org/abs/2503.20800v1
• Date: Mon, 24 Mar 2025 07:35:59 GMT
• Title: Evidencing Unauthorized Training Data from AI Generated Content using Information Isotopes
• Authors: Qi Tao, Yin Jinhua, Cai Dongqi, Xie Yueqi, Wang Huili, Hu Zhiyang, Yang Peiru, Nan Guoshun, Zhou Zhili, Wang Shangguang, Lyu Lingjuan, Huang Yongfeng, Lane Nicholas,
• Abstract summary: In a rush to stay competitive, some institutions may inadvertently or even deliberately include unauthorized data for AI training.<n>We introduce the concept of information isotopes and elucidate their properties in tracing training data within opaque AI systems.<n>We propose an information isotope tracing method designed to identify and provide evidence of unauthorized data usage.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In light of scaling laws, many AI institutions are intensifying efforts to construct advanced AIs on extensive collections of high-quality human data. However, in a rush to stay competitive, some institutions may inadvertently or even deliberately include unauthorized data (like privacy- or intellectual property-sensitive content) for AI training, which infringes on the rights of data owners. Compounding this issue, these advanced AI services are typically built on opaque cloud platforms, which restricts access to internal information during AI training and inference, leaving only the generated outputs available for forensics. Thus, despite the introduction of legal frameworks by various countries to safeguard data rights, uncovering evidence of data misuse in modern opaque AI applications remains a significant challenge. In this paper, inspired by the ability of isotopes to trace elements within chemical reactions, we introduce the concept of information isotopes and elucidate their properties in tracing training data within opaque AI systems. Furthermore, we propose an information isotope tracing method designed to identify and provide evidence of unauthorized data usage by detecting the presence of target information isotopes in AI generations. We conduct experiments on ten AI models (including GPT-4o, Claude-3.5, and DeepSeek) and four benchmark datasets in critical domains (medical data, copyrighted books, and news). Results show that our method can distinguish training datasets from non-training datasets with 99\% accuracy and significant evidence (p-value$<0.001$) by examining a data entry equivalent in length to a research paper. The findings show the potential of our work as an inclusive tool for empowering individuals, including those without expertise in AI, to safeguard their data rights in the rapidly evolving era of AI advancements and applications.

Related papers

• Detecting Dataset Bias in Medical AI: A Generalized and Modality-Agnostic Auditing Framework [8.520644988801243]
  latent bias in machine learning datasets can be amplified during training and/or hidden during testing. We present a data modality-agnostic auditing framework for generating targeted hypotheses about sources of bias. We demonstrate the broad applicability and value of our method by analyzing large-scale medical datasets.
  arXiv  Detail & Related papers  (2025-03-13T02:16:48Z)
• AI Data Readiness Inspector (AIDRIN) for Quantitative Assessment of Data Readiness for AI [0.8553254686016967]
  "Garbage in Garbage Out" is a universally agreed quote by computer scientists from various domains, including Artificial Intelligence (AI)<n>There are no standard methods or frameworks for assessing the "readiness" of data for AI.<n>AIDRIN is a framework covering a broad range of readiness dimensions available in the literature.
  arXiv  Detail & Related papers  (2024-06-27T15:26:39Z)
• Generative AI for Secure and Privacy-Preserving Mobile Crowdsensing [74.58071278710896]
  generative AI has attracted much attention from both academic and industrial fields. Secure and privacy-preserving mobile crowdsensing (SPPMCS) has been widely applied in data collection/ acquirement.
  arXiv  Detail & Related papers  (2024-05-17T04:00:58Z)
• Data Readiness for AI: A 360-Degree Survey [0.9343816282846432]
  This survey examines more than 140 papers published by ACM Digital Library, IEEE Xplore, journals such as Nature, Springer, and Science Direct, and online articles published by prominent AI experts.<n>We propose a taxonomy of data readiness for AI (DRAI) metrics for structured and unstructured datasets.
  arXiv  Detail & Related papers  (2024-04-08T15:19:57Z)
• The Frontier of Data Erasure: Machine Unlearning for Large Language Models [56.26002631481726]
  Large Language Models (LLMs) are foundational to AI advancements. LLMs pose risks by potentially memorizing and disseminating sensitive, biased, or copyrighted information. Machine unlearning emerges as a cutting-edge solution to mitigate these concerns.
  arXiv  Detail & Related papers  (2024-03-23T09:26:15Z)
• On Responsible Machine Learning Datasets with Fairness, Privacy, and Regulatory Norms [56.119374302685934]
  There have been severe concerns over the trustworthiness of AI technologies. Machine and deep learning algorithms depend heavily on the data used during their development. We propose a framework to evaluate the datasets through a responsible rubric.
  arXiv  Detail & Related papers  (2023-10-24T14:01:53Z)
• Human-Centric Multimodal Machine Learning: Recent Advances and Testbed on AI-based Recruitment [66.91538273487379]
  There is a certain consensus about the need to develop AI applications with a Human-Centric approach. Human-Centric Machine Learning needs to be developed based on four main requirements: (i) utility and social good; (ii) privacy and data ownership; (iii) transparency and accountability; and (iv) fairness in AI-driven decision-making processes. We study how current multimodal algorithms based on heterogeneous sources of information are affected by sensitive elements and inner biases in the data.
  arXiv  Detail & Related papers  (2023-02-13T16:44:44Z)
• Trustworthy AI [75.99046162669997]
  Brittleness to minor adversarial changes in the input data, ability to explain the decisions, address the bias in their training data, are some of the most prominent limitations. We propose the tutorial on Trustworthy AI to address six critical issues in enhancing user and public trust in AI systems.
  arXiv  Detail & Related papers  (2020-11-02T20:04:18Z)
• Bias in Multimodal AI: Testbed for Fair Automatic Recruitment [73.85525896663371]
  We study how current multimodal algorithms based on heterogeneous sources of information are affected by sensitive elements and inner biases in the data. We train automatic recruitment algorithms using a set of multimodal synthetic profiles consciously scored with gender and racial biases. Our methodology and results show how to generate fairer AI-based tools in general, and in particular fairer automated recruitment systems.
  arXiv  Detail & Related papers  (2020-04-15T15:58:05Z)

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.