paper-with-me

홈 › Papers

Confident AI

2022-02-12 · Jim Davis

In this paper, we propose "Confident AI" as a means to designing Artificial Intelligence (AI) and Machine Learning (ML) systems with both algorithm and user confidence in model predictions and reported results. The 4 basic tenets of Confident AI are Repeatability, Believability, Sufficiency, and Adaptability. Each of the tenets is used to explore fundamental issues in current AI/ML systems and together provide an overall approach to Confident AI.

📄 PDF Abstract BibTeX arXiv:2202.05957

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine Learning

Similar Papers 제목 키워드 기반

ME-MOMENTUM: EXTRACTING HARD CONFIDENT EXAMPLES FROM NOISILY LABELED DATA

2021-01-01 · ICCV 2021 10 · Yingbin Bai, Tongliang Liu

Examples that are close to the decision boundary—that we term hard examples, are essential to shaping accurate classifiers. Extracting confident examples has been widely studied in the community of learning with noisy …

Learning with noisy labelsMemorization

Network Inversion for Generating Confidently Classified Counterfeits

2025-03-26 · Pirzada Suhail, Amit Sethi

In machine learning, especially with vision classifiers, generating inputs that are confidently classified by the model is essential for understanding its decision boundaries and behavior. However, creating such samples …

Confidential Prompting: Protecting User Prompts from Cloud LLM Providers

2024-09-27 · In Gim, Caihua Li, Lin Zhong

Our work tackles the challenge of securing user inputs in cloud-hosted large language model (LLM) serving while ensuring model confidentiality, output invariance, and compute efficiency. We introduce Secure Partitioned D…

Language ModelingLanguage ModellingLarge Language ModelPrivacy Preserving

Reproducibility and Transparency versus Privacy and Confidentiality: Reflections from a Data Editor

2023-05-23 · Lars Vilhuber

Transparency and reproducibility are often seen in opposition to privacy and confidentiality. Data that need to be kept confidential are seen as an impediment to reproducibility, and privacy would seem to inhibit transpa…

Supercharging Federated Intelligence Retrieval

2026-03-26 · Dimitris Stripelis, Patrick Foley, Mohammad Naseri, William Lindskog-Münzing 외 arxiv

RAG typically assumes centralized access to documents, which breaks down when knowledge is distributed across private data silos. We propose a secure Federated RAG system built using Flower that performs local silo retri…

Text Generation