Related papers: Temperature Scaling Attack Disrupting Model Confid…
Recently, Deep Neural Networks (DNNs) have been achieving impressive results on wide range of tasks. However, they suffer from being well-calibrated. In decision-making applications, such as autonomous driving or medical diagnosing, the…
The prediction reliability of neural networks is important in many applications. Specifically, in safety-critical domains, such as cancer prediction or autonomous driving, a reliable confidence of model's prediction is critical for the…
Conformal prediction is an emerging technique for uncertainty quantification that constructs prediction sets guaranteed to contain the true label with a predefined probability. Previous works often employ temperature scaling to calibrate…
Proper losses such as cross-entropy incentivize classifiers to produce class probabilities that are well-calibrated on the training data. Due to the generalization gap, these classifiers tend to become overconfident on the test data,…
The great performances of deep learning are undeniable, with impressive results over a wide range of tasks. However, the output confidence of these models is usually not well-calibrated, which can be an issue for applications where…
Continual Learning (CL) is recently gaining increasing attention for its ability to enable a single model to learn incrementally from a sequence of new classes. In this scenario, it is important to keep consistent predictive performance…
It is now well known that neural networks can be wrong with high confidence in their predictions, leading to poor calibration. The most common post-hoc approach to compensate for this is to perform temperature scaling, which adjusts the…
We study model confidence calibration in class-incremental learning, where models learn from sequential tasks with different class sets. While existing works primarily focus on accuracy, maintaining calibrated confidence has been largely…
Despite the impressive generalization capabilities of deep neural networks, they have been repeatedly shown to be overconfident when they are wrong. Fixing this issue is known as model calibration, and has consequently received much…
Deep learning and federated learning (FL) are becoming powerful partners for next-generation weather forecasting. Deep learning enables high-resolution spatiotemporal forecasts that can surpass traditional numerical models, while FL allows…
Research interests in the robustness of deep neural networks against domain shifts have been rapidly increasing in recent years. Most existing works, however, focus on improving the accuracy of the model, not the calibration performance…
Manipulation of local training data and local updates, i.e., the poisoning attack, is the main threat arising from the collaborative nature of the federated learning (FL) paradigm. Most existing poisoning attacks aim to manipulate local…
Maintaining the privacy of power system data is essential for protecting sensitive information and ensuring the operation security of critical infrastructure. Therefore, the adoption of centralized deep learning (DL) transient stability…
In many classification applications, the prediction of a deep neural network (DNN) based classifier needs to be accompanied by some confidence indication. Two popular approaches for that aim are: 1) Calibration: modifies the classifier's…
Federated learning (FL) for time series forecasting (TSF) enables clients with privacy-sensitive time series (TS) data to collaboratively learn accurate forecasting models, for example, in energy load prediction. Unfortunately, privacy…
Calibration is central to reliable semantic uncertainty quantification, yet prior work has largely focused on discrimination, neglecting calibration. As calibration and discrimination capture distinct aspects of uncertainty, focusing on…
The operation of critical infrastructures such as the electrical power grid, cellphone towers, and financial institutions relies on precise timing provided by stationary GPS receivers. These GPS devices are vulnerable to a type of spoofing…
We address the problem of uncertainty calibration and introduce a novel calibration method, Parametrized Temperature Scaling (PTS). Standard deep neural networks typically yield uncalibrated predictions, which can be transformed into…
Model poisoning attacks on federated learning (FL) intrude in the entire system via compromising an edge model, resulting in malfunctioning of machine learning models. Such compromised models are tampered with to perform adversary-desired…
The softmax function is a fundamental component in deep learning. This study delves into the often-overlooked parameter within the softmax function, known as "temperature," providing novel insights into the practical and theoretical aspects…