English
Related papers

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

200 papers

Machine learning models are vulnerable to Adversarial Examples: minor perturbations to input samples intended to deliberately cause misclassification. Current defenses against adversarial examples, especially for Deep Neural Networks (DNN),…

Cryptography and Security · Computer Science 2019-01-04 Kathrin Grosse , David Pfaff , Michael Thomas Smith , Michael Backes

Adversarial examples, characterized by imperceptible perturbations, pose significant threats to deep neural networks by misleading their predictions. A critical aspect of these examples is their transferability, allowing them to deceive…

Cryptography and Security · Computer Science 2025-04-22 Yi Yu , Song Xia , Xun Lin , Chenqi Kong , Wenhan Yang , Shijian Lu , Yap-Peng Tan , Alex C. Kot

Fine-tuning large language models on private data for downstream applications poses significant privacy risks in potentially exposing sensitive information. Several popular community platforms now offer convenient distribution of a large…

Machine Learning · Computer Science 2024-09-02 Md Rafi Ur Rashid , Jing Liu , Toshiaki Koike-Akino , Shagufta Mehnaz , Ye Wang

With the widespread deployment of deep learning models, they influence their environment in various ways. The induced distribution shifts can lead to unexpected performance degradation in deployed models. Existing methods to anticipate…

Domain adaptation (DA) aims to transfer knowledge learned from a labeled source domain to an unlabeled or a less labeled but related target domain. Ideally, the source and target distributions should be aligned to each other equally to…

Computer Vision and Pattern Recognition · Computer Science 2022-08-15 Jian Hu , Haowen Zhong , Junchi Yan , Shaogang Gong , Guile Wu , Fei Yang

Semi-supervised machine learning models learn from a (small) set of labeled training examples, and a (large) set of unlabeled training examples. State-of-the-art models can reach within a few percentage points of fully-supervised training,…

Machine Learning · Computer Science 2021-08-11 Nicholas Carlini

While deep neural networks can achieve state-of-the-art performance in many tasks, these models are more fragile than they appear. They are prone to learning spurious correlations in their training data, leading to surprising failure cases.…

Machine Learning · Computer Science 2024-09-05 Jeff Mitchell , Jesús Martínez del Rincón , Niall McLaughlin

Neural NLP models are often miscalibrated and overconfident, assigning high confidence to incorrect predictions and failing to express uncertainty during internal evidence aggregation. This undermines selective prediction and high-stakes…

Artificial Intelligence · Computer Science 2026-03-11 Elias Hossain , Shubhashis Roy Dipta , Subash Neupane , Rajib Rana , Ravid Shwartz-Ziv , Ivan Garibay , Niloofar Yousefi

Language models often pre-train on large unsupervised text corpora, then fine-tune on additional task-specific data. However, typical fine-tuning schemes do not prioritize the examples that they tune on. We show that, if you can prioritize…

Computation and Language · Computer Science 2023-05-12 Ian Osband , Seyed Mohammad Asghari , Benjamin Van Roy , Nat McAleese , John Aslanides , Geoffrey Irving

Unsupervised pretraining, which learns a useful representation using a large amount of unlabeled data to facilitate the learning of downstream tasks, is a critical component of modern large-scale machine learning systems. Despite its…

Machine Learning · Statistics 2023-03-06 Jiawei Ge , Shange Tang , Jianqing Fan , Chi Jin

Most existing unlearnable strategies focus on preventing unauthorized users from training single-task learning (STL) models with personal data. Nevertheless, the paradigm has recently shifted towards multi-task data and multi-task learning…

Machine Learning · Computer Science 2025-05-09 Yi Yu , Song Xia , Siyuan Yang , Chenqi Kong , Wenhan Yang , Shijian Lu , Yap-Peng Tan , Alex C. Kot

Self-training is a powerful approach to deep learning. The key process is to find a pseudo-label for modeling. However, previous self-training algorithms suffer from the over-confidence issue brought by the hard labels, even some…

Computer Vision and Pattern Recognition · Computer Science 2024-05-03 Zijia Wang , Wenbin Yang , Zhisong Liu , Zhen Jia

We theoretically justify the recent empirical finding of [Teh et al., 2025] that a transformer pretrained on synthetically generated data achieves strong performance on empirical Bayes (EB) problems. We take an indirect approach to this…

Machine Learning · Statistics 2026-02-18 Nick Cannella , Anzo Teh , Yanjun Han , Yury Polyanskiy

The pre-training and fine-tuning paradigm has demonstrated its effectiveness and has become the standard approach for tailoring language models to various tasks. Currently, community-based platforms offer easy access to various pre-trained…

Cryptography and Security · Computer Science 2024-09-17 Ruixuan Liu , Tianhao Wang , Yang Cao , Li Xiong

Federated Unlearning (FU) has emerged as a promising solution to respond to the right to be forgotten of clients, by allowing clients to erase their data from global models without compromising model performance. Unfortunately, researchers…

Cryptography and Security · Computer Science 2025-08-12 Wei Wang , Xiangyun Tang , Yajie Wang , Yijing Lin , Tao Zhang , Meng Shen , Dusit Niyato , Liehuang Zhu

Adapting to latent confounded shift remains a core challenge in modern AI. This setting is driven by hidden variables that induce spurious correlations between inputs and outputs during training, leading models to rely on non-causal…

Machine Learning · Computer Science 2026-05-14 Jialin Yu , Yuxiang Zhou , Haoxuan Li , Junchi Yu , Mengyue Yang , Yulan He , Nevin L. Zhang , Philip Torr , Ricardo Silva

Modern text classification models are susceptible to adversarial examples, perturbed versions of the original text indiscernible by humans which get misclassified by the model. Recent works in NLP use rule-based synonym replacement…

Computation and Language · Computer Science 2022-06-22 Siddhant Garg , Goutham Ramakrishnan

When faced with distribution shift at test time, deep neural networks often make inaccurate predictions with unreliable uncertainty estimates. While improving the robustness of neural networks is one promising approach to mitigate this…

Machine Learning · Computer Science 2021-09-28 Aurick Zhou , Sergey Levine

Prompt-based probing has been widely used in evaluating the abilities of pretrained language models (PLMs). Unfortunately, recent studies have discovered such an evaluation may be inaccurate, inconsistent and unreliable. Furthermore, the…

Computation and Language · Computer Science 2022-03-24 Boxi Cao , Hongyu Lin , Xianpei Han , Fangchao Liu , Le Sun

Transfer learning is beneficial by allowing the expressive features of models pretrained on large-scale datasets to be finetuned for the target task of smaller, more domain-specific datasets. However, there is a concern that these…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Angelina Wang , Olga Russakovsky