English
Related papers

Related papers: Overlearning Reveals Sensitive Attributes

200 papers

Neural networks often learn to make predictions that overly rely on spurious correlation existing in the dataset, which causes the model to be biased. While previous work tackles this issue by using explicit labeling on the spuriously…

Machine Learning · Computer Science 2020-11-24 Junhyun Nam , Hyuntak Cha , Sungsoo Ahn , Jaeho Lee , Jinwoo Shin

We introduce a framework to measure how biases change before and after fine-tuning a large scale visual recognition model for a downstream task. Deep learning models trained on increasing amounts of data are known to encode societal biases.…

Computer Vision and Pattern Recognition · Computer Science 2023-03-15 Jaspreet Ranjit , Tianlu Wang , Baishakhi Ray , Vicente Ordonez

Understanding to what extent neural networks memorize training data is an intriguing question with practical and theoretical implications. In this paper we show that in some cases a significant fraction of the training data can in fact be…

Machine Learning · Computer Science 2022-12-06 Niv Haim , Gal Vardi , Gilad Yehudai , Ohad Shamir , Michal Irani

Machine Learning (ML) models have been shown to potentially leak sensitive information, thus raising privacy concerns in ML-driven applications. This inspired recent research on removing the influence of specific data samples from a trained…

Machine Learning · Computer Science 2023-10-30 Youyang Qu , Xin Yuan , Ming Ding , Wei Ni , Thierry Rakotoarivelo , David Smith

Often in language and other areas of cognition, whether two components of an object are identical or not determine whether it is well formed. We call such constraints identity effects. When developing a system to learn well-formedness from…

Computation and Language · Computer Science 2020-05-12 Simone Brugiapaglia , Matthew Liu , Paul Tupper

When training a machine learning classifier on data where one of the classes is intrinsically rare, the classifier will often assign too few sources to the rare class. To address this, it is common to up-weight the examples of the rare…

Machine Learning · Computer Science 2022-08-02 Sean E. Lake , Chao-Wei Tsai

Machine Learning seeks to identify and encode bodies of knowledge within provided datasets. However, data encodes subjective content, which determines the possible outcomes of the models trained on it. Because such subjectivity enables…

Artificial Intelligence · Computer Science 2021-01-29 Zeerak Waseem , Smarika Lulz , Joachim Bingel , Isabelle Augenstein

Collaborative machine learning and related techniques such as federated learning allow multiple participants, each with his own training dataset, to build a joint model by training locally and periodically exchanging model updates. We…

Cryptography and Security · Computer Science 2018-11-02 Luca Melis , Congzheng Song , Emiliano De Cristofaro , Vitaly Shmatikov

Deep Neural Networks are well known for efficiently fitting training data, yet experiencing poor generalization capabilities whenever some kind of bias dominates over the actual task labels, resulting in models learning "shortcuts". In…

Machine Learning · Computer Science 2024-08-12 Pietro Morerio , Ruggero Ragonesi , Vittorio Murino

An increasingly popular machine learning paradigm is to pretrain a neural network (NN) on many tasks offline, then adapt it to downstream tasks, often by re-training only the last linear layer of the network. This approach yields strong…

Machine Learning · Computer Science 2024-06-10 Liam Collins , Hamed Hassani , Mahdi Soltanolkotabi , Aryan Mokhtari , Sanjay Shakkottai

Identifying and mitigating bias in deep learning algorithms has gained significant popularity in the past few years due to its impact on the society. Researchers argue that models trained on balanced datasets with good representation…

Computer Vision and Pattern Recognition · Computer Science 2021-08-17 Puspita Majumdar , Surbhi Mittal , Richa Singh , Mayank Vatsa

Increasing use of machine learning (ML) technologies in privacy-sensitive domains such as medical diagnoses, lifestyle predictions, and business decisions highlights the need to better understand if these ML technologies are introducing…

Cryptography and Security · Computer Science 2022-01-25 Shagufta Mehnaz , Sayanton V. Dibbo , Ehsanul Kabir , Ninghui Li , Elisa Bertino

Natural Language Inference (NLI) models are known to learn from biases and artefacts within their training data, impacting how well they generalise to other unseen datasets. Existing de-biasing approaches focus on preventing the models from…

Computation and Language · Computer Science 2022-05-03 Joe Stacey , Yonatan Belinkov , Marek Rei

It is fair to say that many of the prominent examples of bias in Machine Learning (ML) arise from bias that is there in the training data. In fact, some would argue that supervised ML algorithms cannot be biased, they reflect the data on…

Machine Learning · Computer Science 2021-04-30 William Blanzeisky , Pádraig Cunningham

Machine unlearning seeks to remove the influence of specific training data from a model, a need driven by privacy regulations and robustness concerns. Existing approaches typically modify model parameters, but such updates can be unstable,…

Machine Learning · Computer Science 2026-05-29 Antonio Almudévar , Alfonso Ortega

Bias in classifiers is a severe issue of modern deep learning methods, especially for their application in safety- and security-critical areas. Often, the bias of a classifier is a direct consequence of a bias in the training dataset,…

Computer Vision and Pattern Recognition · Computer Science 2021-03-11 Christian Reimers , Paul Bodesheim , Jakob Runge , Joachim Denzler

Since the recent advent of regulations for data protection (e.g., the General Data Protection Regulation), there has been increasing demand in deleting information learned from sensitive data in pre-trained models without retraining from…

Machine Learning · Computer Science 2024-01-17 Sungmin Cha , Sungjun Cho , Dasol Hwang , Honglak Lee , Taesup Moon , Moontae Lee

Deep neural networks often struggle to learn robust representations in the presence of dataset biases, leading to suboptimal generalization on unbiased datasets. This limitation arises because the models heavily depend on peripheral and…

Machine Learning · Computer Science 2024-12-11 Carlo Alberto Barbano , Enzo Tartaglione , Marco Grangetto

How can we learn a classifier that is "fair" for a protected or sensitive group, when we do not know if the input to the classifier belongs to the protected group? How can we train such a classifier when data on the protected group is…

Machine Learning · Computer Science 2017-07-10 Alex Beutel , Jilin Chen , Zhe Zhao , Ed H. Chi