English
Related papers

Related papers: Querying Kernel Methods Suffices for Reconstructin…

200 papers

In order to fully utilize "big data", it is often required to use "big models". Such models tend to grow with the complexity and size of the training data, and do not make strong parametric assumptions upfront on the nature of the…

Machine Learning · Statistics 2015-04-17 Vikas Sindhwani , Haim Avron

Quantum computers are known to provide speedups over classical state-of-the-art machine learning methods in some specialized settings. For example, quantum kernel methods have been shown to provide an exponential speedup on a learning…

Quantum Physics · Physics 2023-06-21 Abdulkadir Canatar , Evan Peters , Cengiz Pehlevan , Stefan M. Wild , Ruslan Shaydulin

Machine learning algorithms use error function minimization to fit a large set of parameters in a preexisting model. However, error minimization eventually leads to a memorization of the training dataset, losing the ability to generalize to…

Machine Learning · Computer Science 2018-03-16 Fernando Martin-Maroto , Gonzalo G. de Polavieja

Is overparameterization a privacy liability? In this work, we study the effect that the number of parameters has on a classifier's vulnerability to membership inference attacks. We first demonstrate how the number of parameters of a model…

Machine Learning · Computer Science 2023-04-17 Jasper Tan , Daniel LeJeune , Blake Mason , Hamid Javadi , Richard G. Baraniuk

Deep neural networks are widely deployed with quantization techniques to reduce memory and computational costs by lowering the numerical precision of their parameters. While quantization alters model parameters and their outputs, existing…

Machine Learning · Computer Science 2025-12-18 Chenxiang Zhang , Tongxi Qu , Zhong Li , Tian Zhang , Jun Pang , Sjouke Mauw

Most current approaches for protecting privacy in machine learning (ML) assume that models exist in a vacuum. Yet, in reality, these models are part of larger systems that include components for training data filtering, output monitoring,…

We analyze the number of queries that a whitebox adversary needs to make to a private learner in order to reconstruct its training data. For $(\epsilon, \delta)$ DP learners with training data drawn from any arbitrary compact metric space,…

Machine Learning · Computer Science 2024-01-15 Prateeti Mukherjee , Satya Lokam

Recently, an extensive amount of research has been focused on compressing and accelerating Deep Neural Networks (DNN). So far, high compression rate algorithms require part of the training dataset for a low precision calibration, or a…

Machine Learning · Computer Science 2020-04-08 Matan Haroush , Itay Hubara , Elad Hoffer , Daniel Soudry

Machine learning models leak information about the datasets on which they are trained. An adversary can build an algorithm to trace the individual members of a model's training dataset. As a fundamental inference attack, he aims to…

Machine Learning · Statistics 2018-07-17 Milad Nasr , Reza Shokri , Amir Houmansadr

The growing use of large language models in sensitive domains has exposed a critical weakness: the inability to ensure that private information can be permanently forgotten. Yet these systems still lack reliable mechanisms to guarantee that…

Machine Learning · Computer Science 2025-11-14 James Jin Kang , Dang Bui , Thanh Pham , Huo-Chong Ling

Machine learning models' goal is to make correct predictions for specific tasks by learning important properties and patterns from data. By doing so, there is a chance that the model learns properties that are unrelated to its primary task.…

Cryptography and Security · Computer Science 2021-04-28 Mathias P. M. Parisot , Balazs Pejo , Dayana Spagnuelo

Natural language reflects our private lives and identities, making its privacy concerns as broad as those of real life. Language models lack the ability to understand the context and sensitivity of text, and tend to memorize phrases present…

Machine Learning · Statistics 2022-02-15 Hannah Brown , Katherine Lee , Fatemehsadat Mireshghallah , Reza Shokri , Florian Tramèr

There is a growing need for investigating how machine learning models operate. With this work, we aim to understand trained machine learning models by questioning their data preferences. We propose a mathematical framework that allows us to…

Machine Learning · Computer Science 2025-12-22 Eren Mehmet Kıral , Nurşen Aydın , Ş. İlker Birbil

Retrieval-based language models (LMs) have demonstrated improved interpretability, factuality, and adaptability compared to their parametric counterparts, by incorporating retrieved text from external datastores. While it is well known that…

Computation and Language · Computer Science 2023-05-25 Yangsibo Huang , Samyak Gupta , Zexuan Zhong , Kai Li , Danqi Chen

Interpretability is often pointed out as a key requirement for trustworthy machine learning. However, learning and releasing models that are inherently interpretable leaks information regarding the underlying training data. As such…

Artificial Intelligence · Computer Science 2024-04-04 Julien Ferry , Ulrich Aïvodji , Sébastien Gambs , Marie-José Huguet , Mohamed Siala

Deep neural networks have become a primary tool for solving problems in many fields. They are also used for addressing information retrieval problems and show strong performance in several tasks. Training these models requires large,…

Information Retrieval · Computer Science 2017-07-25 Mostafa Dehghani , Hosein Azarbonyad , Jaap Kamps , Maarten de Rijke

Genomic language models (GLMs) have emerged as powerful tools for learning representations of DNA sequences, enabling advances in variant prediction, regulatory element identification, and cross-task transfer learning. However, as these…

Machine Learning · Computer Science 2026-03-11 Alexander Nemecek , Wenbiao Li , Xiaoqian Jiang , Jaideep Vaidya , Erman Ayday

Privacy regulations require the erasure of data from deep learning models. This is a significant challenge that is amplified in Federated Learning, where data remains on clients, making full retraining or coordinated updates often…

Machine Learning · Computer Science 2026-01-27 Antonio Balordi , Lorenzo Manini , Fabio Stella , Alessio Merlo

Privacy attacks on machine learning models aim to identify the data that is used to train such models. Such attacks, traditionally, are studied on static models that are trained once and are accessible by the adversary. Motivated to meet…

Machine Learning · Computer Science 2022-02-09 Ji Gao , Sanjam Garg , Mohammad Mahmoody , Prashant Nalini Vasudevan

This study investigates the risks of exposing confidential chemical structures when machine learning models trained on these structures are made publicly available. We use membership inference attacks, a common method to assess privacy that…

Cryptography and Security · Computer Science 2025-04-18 Fabian P. Krüger , Johan Östman , Lewis Mervin , Igor V. Tetko , Ola Engkvist
‹ Prev 1 3 4 5 6 7 10 Next ›