English
Related papers

Related papers: Ungeneralizable Examples

200 papers

The past a few years have witnessed the great success of large language models, demonstrating powerful capabilities in comprehending textual data and generating human-like languages. Large language models achieve success by being trained on…

Computation and Language · Computer Science 2025-03-20 Estrid He , Tabinda Sarwar , Ibrahim Khalil , Xun Yi , Ke Wang

Neural Networks (NNs) are vulnerable to adversarial examples. Such inputs differ only slightly from their benign counterparts yet provoke misclassifications of the attacked NNs. The required perturbations to craft the examples are often…

Cryptography and Security · Computer Science 2020-09-30 Philip Sperl , Konstantin Böttinger

There is a known tension between the need to analyze personal data to drive business and privacy concerns. Many data protection regulations, including the EU General Data Protection Regulation (GDPR) and the California Consumer Protection…

Cryptography and Security · Computer Science 2022-02-02 Abigail Goldsteen , Gilad Ezov , Ron Shmelkin , Micha Moffie , Ariel Farkash

The detection of previously unseen network attacks remains a major challenge for intrusion detection systems. Although supervised learning methods often perform well on known attack classes, they are limited when new attack types are not…

Cryptography and Security · Computer Science 2026-05-22 Saif Alzubi , Frederic Stahl

Continual Learning models aim to learn a set of tasks under the constraint that the tasks arrive sequentially with no way to access data from previous tasks. The Online Continual Learning framework poses a further challenge where the tasks…

Machine Learning · Computer Science 2024-12-24 Kevin Luong , Michael Thielscher

We propose self-adaptive training -- a unified training algorithm that dynamically calibrates and enhances training processes by model predictions without incurring an extra computational cost -- to advance both supervised and…

Machine Learning · Computer Science 2022-10-17 Lang Huang , Chao Zhang , Hongyang Zhang

Neural networks predictions are unreliable when the input sample is out of the training distribution or corrupted by noise. Being able to detect such failures automatically is fundamental to integrate deep learning algorithms into robotics.…

Computer Vision and Pattern Recognition · Computer Science 2020-02-18 Antonio Loquercio , Mattia Segù , Davide Scaramuzza

Recent research put a big effort in the development of deep learning architectures and optimizers obtaining impressive results in areas ranging from vision to language processing. However little attention has been addressed to the need of a…

Computer Vision and Pattern Recognition · Computer Science 2018-12-20 Gabriele Valvano , Andrea Leo , Daniele Della Latta , Nicola Martini , Gianmarco Santini , Dante Chiappino , Emiliano Ricciardi

Recently, an increasing number of laws have governed the useability of users' privacy. For example, Article 17 of the General Data Protection Regulation (GDPR), the right to be forgotten, requires machine learning applications to remove a…

Machine Learning · Computer Science 2024-11-19 Haibo Zhang , Toru Nakamura , Takamasa Isohara , Kouichi Sakurai

Undirected graphical models are compact representations of joint probability distributions over random variables. To solve inference tasks of interest, graphical models of arbitrary topology can be trained using empirical risk minimization.…

Machine Learning · Computer Science 2020-10-23 Adarsh K. Jeewajee , Leslie P. Kaelbling

The success of deep learning is partly attributed to the availability of massive data downloaded freely from the Internet. However, it also means that users' private data may be collected by commercial organizations without consent and used…

Computer Vision and Pattern Recognition · Computer Science 2022-12-06 Qi Tian , Kun Kuang , Kelu Jiang , Furui Liu , Zhihua Wang , Fei Wu

Adversarial examples causing evasive predictions are widely used to evaluate and improve the robustness of machine learning models. However, current studies focus on supervised learning tasks, relying on the ground-truth data label, a…

Machine Learning · Computer Science 2021-12-09 Chia-Yi Hsu , Pin-Yu Chen , Songtao Lu , Sijia Liu , Chia-Mu Yu

Deep neural networks (DNNs) are vulnerable to adversarial noise. Their adversarial robustness can be improved by exploiting adversarial examples. However, given the continuously evolving attacks, models trained on seen types of adversarial…

Computer Vision and Pattern Recognition · Computer Science 2021-06-10 Dawei Zhou , Tongliang Liu , Bo Han , Nannan Wang , Chunlei Peng , Xinbo Gao

State-of-the-art deep learning models are often trained with a large amount of costly labeled training data. However, requiring exhaustive manual annotations may degrade the model's generalizability in the limited-label regime.…

Computer Vision and Pattern Recognition · Computer Science 2022-08-25 Yanbei Chen , Massimiliano Mancini , Xiatian Zhu , Zeynep Akata

In weakly supervised learning, unbiased risk estimator(URE) is a powerful tool for training classifiers when training and test data are drawn from different distributions. Nevertheless, UREs lead to overfitting in many problem settings when…

Machine Learning · Computer Science 2020-08-25 Yu-Ting Chou , Gang Niu , Hsuan-Tien Lin , Masashi Sugiyama

Deep neural networks (DNNs) have achieved remarkable performance in many tasks, yet they often behave as opaque black boxes. Explanation-guided learning (EGL) methods steer DNNs using human-provided explanations or supervision on model…

Machine Learning · Computer Science 2026-03-03 Chao Chen , Yanhui Chen , Shanshan Lin , Dongsheng Hong , Shu Wu , Xiangwen Liao , Chuanyi Liu

Convolution-based unlearnable examples (UEs) employ class-wise multiplicative convolutional noise to training samples, severely compromising model performance. This fire-new type of UEs have successfully countered all defense mechanisms…

Computer Vision and Pattern Recognition · Computer Science 2024-12-11 Minghui Li , Xianlong Wang , Zhifei Yu , Shengshan Hu , Ziqi Zhou , Longling Zhang , Leo Yu Zhang

How can we effectively remove or ''unlearn'' undesirable information, such as specific features or the influence of individual data points, from a learning outcome while minimizing utility loss and ensuring rigorous guarantees? We introduce…

Machine Learning · Computer Science 2025-12-30 Shizhou Xu , Thomas Strohmer

Large language models are finetuned to refuse questions about hazardous knowledge, but these protections can often be bypassed. Unlearning methods aim at completely removing hazardous capabilities from models and make them inaccessible to…

Machine Learning · Computer Science 2025-06-03 Jakub Łucki , Boyi Wei , Yangsibo Huang , Peter Henderson , Florian Tramèr , Javier Rando

Evidential Deep Learning (EDL) has emerged as an efficient, sampling-free strategy for uncertainty estimation. A series of EDL variants have been proposed to address specific limitations of the original framework, achieving notable success.…

Machine Learning · Computer Science 2026-05-26 Yuanye Liu , Yibo Gao , Yuanyang Chen , Xiahai Zhuang