English
Related papers

Related papers: When Priors Backfire: On the Vulnerability of Unle…

200 papers

Models prone to spurious correlations in training data often produce brittle predictions and introduce unintended biases. Addressing this challenge typically involves methods relying on prior knowledge and group annotation to remove…

Machine Learning · Computer Science 2025-07-21 Md Rifat Arefin , Yan Zhang , Aristide Baratin , Francesco Locatello , Irina Rish , Dianbo Liu , Kenji Kawaguchi

Multimodal contrastive learning (MCL) has shown remarkable advances in zero-shot classification by learning from millions of image-caption pairs crawled from the Internet. However, this reliance poses privacy risks, as hackers may…

Multimedia · Computer Science 2024-07-29 Xinwei Liu , Xiaojun Jia , Yuan Xun , Siyuan Liang , Xiaochun Cao

Machine Unlearning (MU) enables Large Language Models (LLMs) to remove unsafe or outdated information. However, existing work assumes that all facts are equally forgettable and largely ignores whether the forgotten knowledge originates from…

Computation and Language · Computer Science 2026-05-15 Borisiuk Anna , Andrey Savchenko , Alexander Panchenko , Elena Tutubalina

Intelligent agents must be able to articulate its own uncertainty. In this work, we show that pre-trained sequence models are naturally capable of probabilistic reasoning over exchangeable data points -- forming informed beliefs and…

Machine Learning · Statistics 2024-12-02 Naimeng Ye , Hongseok Namkoong

Growing concerns over data privacy and security highlight the importance of machine unlearning--removing specific data influences from trained models without full retraining. Techniques like Membership Inference Attacks (MIAs) are widely…

Machine Learning · Computer Science 2025-06-09 Cheng-Long Wang , Qi Li , Zihang Xiang , Yinzhi Cao , Di Wang

Conventional Bayesian Neural Networks (BNNs) are unable to leverage unlabelled data to improve their predictions. To overcome this limitation, we introduce Self-Supervised Bayesian Neural Networks, which use unlabelled data to learn models…

Machine Learning · Computer Science 2024-09-02 Mrinank Sharma , Tom Rainforth , Yee Whye Teh , Vincent Fortuin

Backdoor unlearning aims to remove backdoor-related information while preserving the model's original functionality. However, existing unlearning methods mainly focus on recovering trigger patterns but fail to restore the correct semantic…

Cryptography and Security · Computer Science 2025-07-15 Yanghao Su , Jie Zhang , Yiming Li , Tianwei Zhang , Qing Guo , Weiming Zhang , Nenghai Yu , Nils Lukas , Wenbo Zhou

It is known that neural networks have the problem of being over-confident when directly using the output label distribution to generate uncertainty measures. Existing methods mainly resolve this issue by retraining the entire model to…

Machine Learning · Computer Science 2022-12-15 Maohao Shen , Yuheng Bu , Prasanna Sattigeri , Soumya Ghosh , Subhro Das , Gregory Wornell

The susceptibility of deep learning models to adversarial perturbations has stirred renewed attention in adversarial examples resulting in a number of attacks. However, most of these attacks fail to encompass a large spectrum of adversarial…

Active learning frameworks offer efficient data annotation without remarkable accuracy degradation. In other words, active learning starts training the model with a small size of labeled data while exploring the space of unlabeled data in…

Machine Learning · Computer Science 2022-04-22 Salman Mohamadi , Hamidreza Amindavar

Fitting complex patterns in the training data, such as reasoning and commonsense, is a key challenge for language pre-training. According to recent studies and our empirical observations, one possible reason is that some easy-to-fit…

Computation and Language · Computer Science 2021-12-06 Chen Xing , Wenhao Liu , Caiming Xiong

Deep neural network-based classifiers are prone to errors when processing adversarial examples (AEs). AEs are minimally perturbed input data undetectable to humans posing significant risks to security-dependent applications. Hence,…

Cryptography and Security · Computer Science 2026-01-05 Fumiya Morimoto , Ryuto Morita , Satoshi Ono

As deep learning models are becoming larger and data-hungrier, there are growing ethical, legal and technical concerns over use of data: in practice, agreements on data use may change over time, rendering previously-used training data…

Machine Learning · Computer Science 2024-05-20 Nazanin Mohammadi Sepahvand , Vincent Dumoulin , Eleni Triantafillou , Gintare Karolina Dziugaite

Language models can learn a range of capabilities from unsupervised training on text corpora. However, to solve a particular problem (such as text summarization) it is typically necessary to fine-tune them on a task-specific dataset. It is…

Computation and Language · Computer Science 2022-03-16 Adam Gleave , Geoffrey Irving

AI models need to be unlearned to fulfill the requirements of legal acts such as the AI Act or GDPR, and also because of the need to remove toxic content, debiasing, the impact of malicious instances, or changes in the data distribution…

Machine Learning · Computer Science 2025-07-16 Patryk Jasiorski , Marek Klonowski , Michał Woźniak

In practical scenarios where training data is limited, many predictive signals in the data can be rather from some biases in data acquisition (i.e., less generalizable), so that one cannot prevent a model from co-adapting on such…

Machine Learning · Computer Science 2023-03-27 Jongheon Jeong , Sihyun Yu , Hankook Lee , Jinwoo Shin

Modern neural networks have proven to be powerful function approximators, providing state-of-the-art performance in a multitude of applications. They however fall short in their ability to quantify confidence in their predictions - this is…

Machine Learning · Statistics 2020-06-29 Alex J. Chan , Ahmed M. Alaa , Zhaozhi Qian , Mihaela van der Schaar

Machine learning models trained on vast amounts of real or synthetic data often achieve outstanding predictive performance across various domains. However, this utility comes with increasing concerns about privacy, as the training data may…

Cryptography and Security · Computer Science 2024-07-09 Binhao Ma , Tianhang Zheng , Hongsheng Hu , Di Wang , Shuo Wang , Zhongjie Ba , Zhan Qin , Kui Ren

Bayes' rule has enabled innumerable powerful algorithms of statistical signal processing and statistical machine learning. However, when model misspecifications exist in prior and/or data distributions, the direct application of Bayes' rule…

Signal Processing · Electrical Eng. & Systems 2026-02-13 Shixiong Wang

This work addresses the unsupervised domain adaptation problem, especially in the case of class labels in the target domain being only a subset of those in the source domain. Such a partial transfer setting is realistic but challenging and…

Computer Vision and Pattern Recognition · Computer Science 2020-07-17 Jian Liang , Yunbo Wang , Dapeng Hu , Ran He , Jiashi Feng