English
Related papers

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

200 papers

Jointly extracting entity pairs and their relations is challenging when working on distantly-supervised data with ambiguous or noisy labels. To mitigate such impact, we propose uncertainty-aware bootstrap learning, which is motivated by the…

Computation and Language · Computer Science 2023-06-12 Yufei Li , Xiao Yu , Yanchi Liu , Haifeng Chen , Cong Liu

Corruptions due to data perturbations and label noise are prevalent in the datasets from unreliable sources, which poses significant threats to model training. Despite existing efforts in developing robust models, current learning methods…

Machine Learning · Computer Science 2024-05-08 Peng-Fei Zhang , Zi Huang , Xin-Shun Xu , Guangdong Bai

Large pre-trained models have achieved notable success across a range of downstream tasks. However, recent research shows that a type of adversarial attack ($\textit{i.e.,}$ backdoor attack) can manipulate the behavior of machine learning…

Artificial Intelligence · Computer Science 2024-10-29 Dongliang Guo , Mengxuan Hu , Zihan Guan , Junfeng Guo , Thomas Hartvigsen , Sheng Li

Machine learning models achieve state-of-the-art performance on many supervised learning tasks. However, prior evidence suggests that these models may learn to rely on shortcut biases or spurious correlations (intuitively, correlations that…

Machine Learning · Computer Science 2021-08-31 Sindhu C. M. Gowda , Shalmali Joshi , Haoran Zhang , Marzyeh Ghassemi

Deep learning models often achieve high performance by inadvertently learning spurious correlations between targets and non-essential features. For example, an image classifier may identify an object via its background that spuriously…

Machine Learning · Computer Science 2025-06-19 Guangtao Zheng , Wenqian Ye , Aidong Zhang

Existing similarity-based weakly supervised learning approaches often rely on precise similarity annotations between data pairs, which may inadvertently expose sensitive label information and raise privacy risks. To mitigate this issue, we…

Machine Learning · Computer Science 2025-09-16 Meng Wei , Zhongnian Li , Peng Ying , Xinzheng Xu

Machine unlearning, which enables a model to forget specific data, is crucial for ensuring data privacy and model reliability. However, its effectiveness can be severely undermined in real-world scenarios where models learn unintended…

Machine Learning · Computer Science 2026-02-26 JuneHyoung Kwon , MiHyeon Kim , Eunju Lee , Yoonji Lee , Seunghoon Lee , YoungBin Kim

Uncertainty calibration is crucial for various machine learning applications, yet it remains challenging. Many models exhibit hallucinations - confident yet inaccurate responses - due to miscalibrated confidence. Here, we show that the…

Machine Learning · Computer Science 2025-03-28 Jeonghwan Cheon , Se-Bum Paik

Fine-tuning lets practitioners repurpose aligned large language models (LLMs) for new domains, yet recent work reveals emergent misalignment (EMA): Even a small, domain-specific fine-tune can induce harmful behaviors far outside the target…

Machine Learning · Computer Science 2026-03-06 David Kaczér , Magnus Jørgenvåg , Clemens Vetter , Esha Afzal , Robin Haselhorst , Lucie Flek , Florian Mai

Text classifiers built on Pre-trained Language Models (PLMs) have achieved remarkable progress in various tasks including sentiment analysis, natural language inference, and question-answering. However, the occurrence of uncertain…

Computation and Language · Computer Science 2023-06-07 Jiazheng Li , Zhaoyue Sun , Bin Liang , Lin Gui , Yulan He

We present a novel approach for training deep neural networks in a Bayesian way. Classical, i.e. non-Bayesian, deep learning has two major drawbacks both originating from the fact that network parameters are considered to be deterministic.…

Machine Learning · Statistics 2019-03-11 Konstantin Posch , Jan Steinbrener , Jürgen Pilz

Adversarial examples (AEs) are images that can mislead deep neural network (DNN) classifiers via introducing slight perturbations into original images. This security vulnerability has led to vast research in recent years because it can…

Machine Learning · Computer Science 2020-12-25 Ruqi Bai , Saurabh Bagchi , David I. Inouye

Verifying whether the machine unlearning process has been properly executed is critical but remains underexplored. Some existing approaches propose unlearning verification methods based on backdooring techniques. However, these methods…

Machine Learning · Computer Science 2026-02-04 Weiqi Wang , Zhiyi Tian , Chenhan Zhang , Luoyu Chen , Shui Yu

The recently proposed unlabeled-unlabeled (UU) classification method allows us to train a binary classifier only from two unlabeled datasets with different class priors. Since this method is based on the empirical risk minimization, it…

Machine Learning · Computer Science 2020-04-01 Nan Lu , Tianyi Zhang , Gang Niu , Masashi Sugiyama

Assessing the exploitability of software vulnerabilities at the time of disclosure is difficult and error-prone, as features extracted via technical analysis by existing metrics are poor predictors for exploit development. Moreover,…

Cryptography and Security · Computer Science 2022-02-04 Octavian Suciu , Connor Nelson , Zhuoer Lyu , Tiffany Bao , Tudor Dumitras

This paper addresses the ethical concerns arising from the use of unauthorized public data in deep learning models and proposes a novel solution. Specifically, building on the work of Huang et al. (2021), we extend their bi-level…

Computation and Language · Computer Science 2024-10-15 Xinzhe Li , Ming Liu , Shang Gao

Many studies have shown various biases targeting different demographic groups in language models, amplifying discrimination and harming fairness. Recent parameter modification debiasing approaches significantly degrade core capabilities…

Computation and Language · Computer Science 2025-10-01 Dianqing Liu , Yi Liu , Guoqing Jin , Zhendong Mao

Deep neural networks do not discriminate between spurious and causal patterns, and will only learn the most predictive ones while ignoring the others. This shortcut learning behaviour is detrimental to a network's ability to generalize to…

Machine Learning · Computer Science 2023-01-11 Thomas Duboudin , Emmanuel Dellandréa , Corentin Abgrall , Gilles Hénaff , Liming Chen

Existing popular unsupervised embedding learning methods focus on enhancing the instance-level local discrimination of the given unlabeled images by exploring various negative data. However, the existed sample outliers which exhibit large…

Computer Vision and Pattern Recognition · Computer Science 2021-07-20 Jiahuan Zhou , Yansong Tang , Bing Su , Ying Wu

Unlearnable data (ULD) has emerged as an innovative defense technique to prevent machine learning models from learning meaningful patterns from specific data, thus protecting data privacy and security. By introducing perturbations to the…

Machine Learning · Computer Science 2025-04-02 Jiahao Li , Yiqiang Chen , Yunbing Xing , Yang Gu , Xiangyuan Lan