Related papers: tsdataleaks: An R Package to Detect Potential Data…

Differential Privacy (DP) has received increasing attention as a rigorous privacy framework. Many existing studies employ traditional DP mechanisms (e.g., the Laplace mechanism) as primitives to continuously release private data for…

Recent work has demonstrated the successful extraction of training data from generative language models. However, it is not evident whether such extraction is feasible in text classification models since the training objective is to predict…

Load forecasting plays a critical role in the operation and planning of power systems. By using input features such as historical loads and weather forecasts, system operators and utilities build forecast models to guide decision making in…

Time series data are ubiquitous nowadays. Whereas most of the literature on the topic deals with real-valued time series, categorical time series have received much less attention. However, the development of data mining techniques for this…

Time-series forecasting has been an important research domain for so many years. Its applications include ECG predictions, sales forecasting, weather conditions, even COVID-19 spread predictions. These applications have motivated many…

Machine-learning models contain information about the data they were trained on. This information leaks either through the model itself or through predictions made by the model. Consequently, when the training data contains sensitive…

Information leakage can have dramatic consequences on systems security. Among harmful information leaks, the timing information leakage occurs whenever an attacker successfully deduces confidential internal information. In this work, we…

Leaking information about the execution behavior of critical real-time tasks may lead to serious consequences, including violations of temporal constraints and even severe failures. We study information leakage for a special class of…

Recent studies have discovered that large language models (LLM) may be ``fooled'' to output private information, including training data, system prompts, and personally identifiable information, under carefully crafted adversarial prompts.…

Link prediction is a fundamental problem in network science, aiming to infer potential or missing links based on observed network structures. With the increasing adoption of parameterized models, the rigor of evaluation protocols has become…

In machine learning, a bias occurs whenever training sets are not representative for the test data, which results in unreliable models. The most common biases in data are arguably class imbalance and covariate shift. In this work, we aim to…

With the growing emphasis on users' privacy, federated learning has become more and more popular. Many architectures have been raised for a better security. Most architecture work on the assumption that data's gradient could not leak…

Data competitions rely on real-time leaderboards to rank competitor entries and stimulate algorithm improvement. While such competitions have become quite popular and prevalent, particularly in supervised learning formats, their…

The success of Large Language Models (LLMs) relies heavily on the huge amount of pre-training data learned in the pre-training phase. The opacity of the pre-training process and the training data causes the results of many benchmark tests…

Leakage of confidential information represents a serious security risk. Despite a number of novel, theoretical advances, it has been unclear if and how quantitative approaches to measuring leakage of confidential information could be…

Missing values in datasets are a well-known problem and there are quite a lot of R packages offering imputation functions. But while imputation in general is well covered within R, it is hard to find functions for imputation of univariate…

There is a bias in the inference pipeline of most diffusion models. This bias arises from a signal leak whose distribution deviates from the noise distribution, creating a discrepancy between training and inference processes. We demonstrate…

Systems that rely on forecasts to make decisions, e.g. control or energy trading systems, require frequent updates of the forecasts. Usually, the forecasts are updated whenever new observations become available, hence in an online setting.…

In the current context of Big Data, the nature of many forecasting problems has changed from predicting isolated time series to predicting many time series from similar sources. This has opened up the opportunity to develop competitive…

Recent advances in neural network based language models lead to successful deployments of such models, improving user experience in various applications. It has been demonstrated that strong performance of language models comes along with…