Training Data Attribution (TDA): Examining Its Adoption & Use Cases

• URL: http://arxiv.org/abs/2501.12642v1
• Date: Wed, 22 Jan 2025 05:03:51 GMT
• Title: Training Data Attribution (TDA): Examining Its Adoption & Use Cases
• Authors: Deric Cheng, Juhan Bae, Justin Bullock, David Kristofferson,
• Abstract summary: This report investigates Training Data Attribution (TDA) and its potential importance to and tractability for reducing extreme risks from AI.<n>We discuss the plausibility and amount of effort it would take to bring existing TDA research efforts from their current state, to an efficient and accurate tool for TDA inference.<n>We list and discuss a series of policies and systems that may be enabled by TDA.
• Score: 5.256285764938807
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This report investigates Training Data Attribution (TDA) and its potential importance to and tractability for reducing extreme risks from AI. First, we discuss the plausibility and amount of effort it would take to bring existing TDA research efforts from their current state, to an efficient and accurate tool for TDA inference that can be run on frontier-scale LLMs. Next, we discuss the numerous research benefits AI labs will expect to see from using such TDA tooling. Then, we discuss a key outstanding bottleneck that would limit such TDA tooling from being accessible publicly: AI labs' willingness to disclose their training data. We suggest ways AI labs may work around these limitations, and discuss the willingness of governments to mandate such access. Assuming that AI labs willingly provide access to TDA inference, we then discuss what high-level societal benefits you might see. We list and discuss a series of policies and systems that may be enabled by TDA. Finally, we present an evaluation of TDA's potential impact on mitigating large-scale risks from AI systems.

Related papers

• Artificial Intelligence of Things: A Survey [14.204632921719933]
  The integration of the Internet of Things (IoT) and modern Artificial Intelligence (AI) has given rise to a new paradigm known as the Artificial Intelligence of Things (AIoT) We examine AIoT literature related to sensing, computing, and networking & communication, which form the three key components of AIoT. In addition to advancements in these areas, we review domain-specific AIoT systems that are designed for various important application domains.
  arXiv  Detail & Related papers  (2024-10-25T22:45:58Z)
• Using AI Alignment Theory to understand the potential pitfalls of regulatory frameworks [55.2480439325792]
  This paper critically examines the European Union's Artificial Intelligence Act (EU AI Act) Uses insights from Alignment Theory (AT) research, which focuses on the potential pitfalls of technical alignment in Artificial Intelligence. As we apply these concepts to the EU AI Act, we uncover potential vulnerabilities and areas for improvement in the regulation.
  arXiv  Detail & Related papers  (2024-10-10T17:38:38Z)
• Towards User-Focused Research in Training Data Attribution for Human-Centered Explainable AI [17.453208581487495]
  XAI aims to make AI understandable and useful to humans, but it has been criticised for relying too much on formalism and solutionism. We show how the XAI research community should adopt a top-down, user-focused perspective to ensure user relevance.
  arXiv  Detail & Related papers  (2024-09-25T14:40:26Z)
• AI for IT Operations (AIOps) on Cloud Platforms: Reviews, Opportunities and Challenges [60.56413461109281]
  Artificial Intelligence for IT operations (AIOps) aims to combine the power of AI with the big data generated by IT Operations processes. We discuss in depth the key types of data emitted by IT Operations activities, the scale and challenges in analyzing them, and where they can be helpful. We categorize the key AIOps tasks as - incident detection, failure prediction, root cause analysis and automated actions.
  arXiv  Detail & Related papers  (2023-04-10T15:38:12Z)
• Dataset Distillation: A Comprehensive Review [76.26276286545284]
  dataset distillation (DD) aims to derive a much smaller dataset containing synthetic samples, based on which the trained models yield performance comparable with those trained on the original dataset. This paper gives a comprehensive review and summary of recent advances in DD and its application.
  arXiv  Detail & Related papers  (2023-01-17T17:03:28Z)
• The Role of AI in Drug Discovery: Challenges, Opportunities, and Strategies [97.5153823429076]
  The benefits, challenges and drawbacks of AI in this field are reviewed. The use of data augmentation, explainable AI, and the integration of AI with traditional experimental methods are also discussed.
  arXiv  Detail & Related papers  (2022-12-08T23:23:39Z)
• Exploring Adversarially Robust Training for Unsupervised Domain Adaptation [71.94264837503135]
  Unsupervised Domain Adaptation (UDA) methods aim to transfer knowledge from a labeled source domain to an unlabeled target domain. This paper explores how to enhance the unlabeled data robustness via AT while learning domain-invariant features for UDA. We propose a novel Adversarially Robust Training method for UDA accordingly, referred to as ARTUDA.
  arXiv  Detail & Related papers  (2022-02-18T17:05:19Z)
• EvaLDA: Efficient Evasion Attacks Towards Latent Dirichlet Allocation [9.277398460006394]
  We study whether Latent Dirichlet Allocation models are vulnerable to adversarial perturbations during inference time. We propose a novel and efficient algorithm, EvaLDA, to solve it. Our work provides significant insights into the power and limitations of evasion attacks to LDA models.
  arXiv  Detail & Related papers  (2020-12-09T04:57:20Z)
• Artificial Intelligence for UAV-enabled Wireless Networks: A Survey [72.10851256475742]
  Unmanned aerial vehicles (UAVs) are considered as one of the promising technologies for the next-generation wireless communication networks. Artificial intelligence (AI) is growing rapidly nowadays and has been very successful. We provide a comprehensive overview of some potential applications of AI in UAV-based networks.
  arXiv  Detail & Related papers  (2020-09-24T07:11:31Z)
• On the Convergence of Artificial Intelligence and Distributed Ledger Technology: A Scoping Review and Future Research Agenda [0.0]
  Developments in Artificial Intelligence (AI) and Distributed Ledger Technology (DLT) lead to lively debates in academia and practice. DLT has the potential to create consensus over data among a group of participants in uncertain environments.
  arXiv  Detail & Related papers  (2020-01-29T18:57:27Z)

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.