Related papers: Robust Conformal Outlier Detection under Contamina…

Methods for split conformal prediction leverage calibration samples to transform any prediction rule into a set-prediction rule that complies with a target coverage probability. Existing methods provide remarkably strong performance…

Multivariate time series (MTS) anomaly detection is essential for maintaining the reliability of industrial systems, yet real-world deployment is hindered by two critical challenges: training data contamination (noises and hidden anomalies)…

Early stopping based on hold-out data is a popular regularization technique designed to mitigate overfitting and increase the predictive accuracy of neural networks. Models trained with early stopping often provide relatively accurate…

While the utilisation of different methods of outliers correction has been shown to counteract the inferential error produced by the presence of contaminating data not belonging to the studied population; the effects produced by their…

We present a conformal inference method for constructing lower prediction bounds for survival times from right-censored data, extending recent approaches designed for more restrictive type-I censoring scenarios. The proposed method imputes…

Modern artificial intelligence systems require calibrated uncertainty estimates that remain reliable in sequential and non-stationary environments. Online conformal prediction (OCP) addresses this challenge through adaptively updated…

Many modern datasets are collected automatically and are thus easily contaminated by outliers. This led to a regain of interest in robust estimation, including new notions of robustness such as robustness to adversarial contamination of the…

In next-generation communications and networks, machine learning (ML) models are expected to deliver not only accurate predictions but also well-calibrated confidence scores that reflect the true likelihood of correct decisions. This paper…

The literature on test set contamination largely focuses on detection, but the correction of contaminated test scores is underexplored. Our core proposal is to spike the training data by intentionally contaminating some test examples at…

Conformal prediction is a model-agnostic approach to generating prediction sets that cover the true class with a high probability. Although its prediction set size is expected to capture aleatoric uncertainty, there is a lack of evidence…

Data poisoning attacks, in which an adversary corrupts a training set with the goal of inducing specific desired mistakes, have raised substantial concern: even just the possibility of such an attack can make a user no longer trust the…

Deep image classification models trained on vast amounts of web-scraped data are susceptible to data poisoning - a mechanism for backdooring models. A small number of poisoned samples seen during training can severely undermine a model's…

Conformal prediction constructs a confidence set for an unobserved response of a feature vector based on previous identically distributed and exchangeable observations of responses and features. It has a coverage guarantee at any nominal…

The presence of outlying observations may adversely affect statistical testing procedures that result in unstable test statistics and unreliable inferences depending on the distortion in parameter estimates. In spite of the fact that the…

Normalizing flows are prominent deep generative models that provide tractable probability distributions and efficient density estimation. However, they are well known to fail while detecting Out-of-Distribution (OOD) inputs as they directly…

The best subset selection (or "best subsets") estimator is a classic tool for sparse regression, and developments in mathematical optimization over the past decade have made it more computationally tractable than ever. Notwithstanding its…

The opacity in developing large language models (LLMs) is raising growing concerns about the potential contamination of public benchmarks in the pre-training data. Existing contamination detection methods are typically based on the text…

Large language models (LLMs) are increasingly exposed to data contamination, i.e., performance gains driven by prior exposure of test datasets rather than generalization. However, in the context of tabular data, this problem is largely…

Contaminated or adulterated food poses a substantial risk to human health. Given sets of labeled web texts for training, Machine Learning and Natural Language Processing can be applied to automatically detect such risks. We publish a…

Ensuring the reliability of machine learning-based intrusion detection systems remains a critical challenge in Internet of Things (IoT) environments, particularly as data poisoning attacks increasingly threaten the integrity of model…