English
Related papers

Related papers: A General Framework for Data-Use Auditing of ML Mo…

200 papers

With widespread adoption of AI models for important decision making, ensuring reliability of such models remains an important challenge. In this paper, we present an end-to-end generic framework for testing AI Models which performs…

Machine Learning · Computer Science 2021-02-12 Aniya Aggarwal , Samiulla Shaikh , Sandeep Hans , Swastik Haldar , Rema Ananthanarayanan , Diptikalyan Saha

We study the feasibility of conducting alignment audits: investigations into whether models have undesired objectives. As a testbed, we train a language model with a hidden objective. Our training pipeline first teaches the model about…

ML models have errors when used for predictions. The errors are unknown but can be quantified by model uncertainty. When multiple ML models are trained using the same training points, their model uncertainties may be statistically…

Machine Learning · Statistics 2025-09-23 Xiaoping Du

Commercial large language models are typically deployed as black-box API services, requiring users to trust providers to execute inference correctly and report token usage honestly. We present IMMACULATE, a practical auditing framework that…

Cryptography and Security · Computer Science 2026-02-27 Yanpei Guo , Wenjie Qu , Linyu Wu , Shengfang Zhai , Lionel Z. Wang , Ming Xu , Yue Liu , Binhang Yuan , Dawn Song , Jiaheng Zhang

Machine learning models have spread to almost every area of life. They are successfully applied in biology, medicine, finance, physics, and other fields. With modern software it is easy to train even a~complex model that fits the training…

Computation · Statistics 2020-05-27 Alicja Gosiewska , Przemyslaw Biecek

As we rely on machine learning (ML) models to make more consequential decisions, the issue of ML models perpetuating or even exacerbating undesirable historical biases (e.g., gender and racial biases) has come to the fore of the public's…

Machine Learning · Statistics 2021-04-01 Subha Maity , Songkai Xue , Mikhail Yurochkin , Yuekai Sun

Training large language models (LLMs) for external tool usage is a rapidly expanding field, with recent research focusing on generating synthetic data to address the shortage of available data. However, the absence of systematic data…

Machine Learning · Computer Science 2024-09-27 Shadi Iskander , Nachshon Cohen , Zohar Karnin , Ori Shapira , Sofia Tolmach

How much does a machine learning algorithm leak about its training data, and why? Membership inference attacks are used as an auditing tool to quantify this leakage. In this paper, we present a comprehensive \textit{hypothesis testing…

Machine Learning · Computer Science 2022-09-14 Jiayuan Ye , Aadyaa Maddi , Sasi Kumar Murakonda , Vincent Bindschaedler , Reza Shokri

Machine learning (ML) models often exhibit bias that can exacerbate inequities in biomedical applications. Fairness auditing, the process of evaluating a model's performance across subpopulations, is critical for identifying and mitigating…

Methodology · Statistics 2026-05-19 Jianhui Gao , Jessica Gronsbell

The increasing use of machine-learning (ML) enabled systems in critical tasks fuels the quest for novel verification and validation techniques yet grounded in accepted system assurance principles. In traditional system development,…

Machine Learning · Computer Science 2020-02-11 Taejoon Byun , Sanjai Rayadurgam

Machine Learning (ML) models have gained popularity in medical imaging analysis given their expert level performance in many medical domains. To enhance the trustworthiness, acceptance, and regulatory compliance of medical imaging models…

Human-Computer Interaction · Computer Science 2025-06-06 Mischa Dombrowski , Andrea Prenner , Bernhard Kainz

Countless domains rely on Machine Learning (ML) models, including safety-critical domains, such as autonomous driving, which this paper focuses on. While the black box nature of ML is simply a nuisance in some domains, in safety-critical…

Artificial Intelligence · Computer Science 2024-06-24 Lynn Vonderhaar , Timothy Elvira , Tyler Procko , Omar Ochoa

Data auditing is a process to verify whether certain data have been removed from a trained model. A recently proposed method (Liu et al. 20) uses Kolmogorov-Smirnov (KS) distance for such data auditing. However, it fails under certain…

Machine Learning · Computer Science 2021-09-15 Yangsibo Huang , Xiaoxiao Li , Kai Li

With the surge of large language models (LLMs), Large Vision-Language Models (VLMs)--which integrate vision encoders with LLMs for accurate visual grounding--have shown great potential in tasks like generalist agents and robotic control.…

Computer Vision and Pattern Recognition · Computer Science 2025-04-28 Hongyu Zhu , Sichu Liang , Wenwen Wang , Boheng Li , Tongxin Yuan , Fangqi Li , ShiLin Wang , Zhuosheng Zhang

With the rapid integration of Machine Learning (ML) in business applications and processes, it is crucial to ensure the quality, reliability and reproducibility of such systems. We suggest a methodical approach towards ML system quality…

Machine Learning · Computer Science 2025-02-26 Angelantonio Castelli , Georgios Christos Chouliaras , Dmitri Goldenberg

Production machine learning (ML) systems fail silently -- not with crashes, but through wrong decisions. While observability is recognized as critical for ML operations, there is a lack empirical evidence of what practitioners actually…

Software Engineering · Computer Science 2025-10-29 Joran Leest , Ilias Gerostathopoulos , Patricia Lago , Claudia Raibulet

Machine learning models can leak information regarding the dataset they have trained. In this paper, we present the first membership inference attack against black-boxed object detection models that determines whether the given data records…

Computer Vision and Pattern Recognition · Computer Science 2020-01-29 Yeachan Park , Myungjoo Kang

We introduce Matched Machine Learning, a framework that combines the flexibility of machine learning black boxes with the interpretability of matching, a longstanding tool in observational causal inference. Interpretability is paramount in…

Methodology · Statistics 2023-04-05 Marco Morucci , Cynthia Rudin , Alexander Volfovsky

Membership inference attacks are designed to determine, using black box access to trained models, whether a particular example was used in training or not. Membership inference can be formalized as a hypothesis testing problem. The most…

Machine Learning · Computer Science 2023-07-10 Martin Bertran , Shuai Tang , Michael Kearns , Jamie Morgenstern , Aaron Roth , Zhiwei Steven Wu

The quality of underlying training data is very crucial for building performant machine learning models with wider generalizabilty. However, current machine learning (ML) tools lack streamlined processes for improving the data quality. So,…

Machine Learning · Computer Science 2021-12-16 Atindriyo Sanyal , Vikram Chatterji , Nidhi Vyas , Ben Epstein , Nikita Demir , Anthony Corletti