Related papers: Calibration Attacks: A Comprehensive Study of Adve…
Since neural classifiers are known to be sensitive to adversarial perturbations that alter their accuracy, \textit{certification methods} have been developed to provide provable guarantees on the insensitivity of their predictions to such…
Machine-learning models can be fooled by adversarial examples, i.e., carefully-crafted input perturbations that force models to output wrong predictions. While uncertainty quantification has been recently proposed to detect adversarial…
Proper confidence calibration of deep neural networks is essential for reliable predictions in safety-critical tasks. Miscalibration can lead to model over-confidence and/or under-confidence; i.e., the model's confidence in its prediction…
Machine learning has seen tremendous advances in the past few years, which has lead to deep learning models being deployed in varied applications of day-to-day life. Attacks on such models using perturbations, particularly in real-life…
Adversarial training yields robust models against a specific threat model, e.g., $L_\infty$ adversarial examples. Typically robustness does not generalize to previously unseen threat models, e.g., other $L_p$ norms, or larger perturbations.…
Deep learning models (with neural networks) have been widely used in challenging tasks such as computer-aided disease diagnosis based on medical images. Recent studies have shown deep diagnostic models may not be robust in the inference…
Despite their impressive predictive performance, GNNs often exhibit poor confidence calibration, i.e., their predicted confidence scores do not accurately reflect true correctness likelihood. This issue raises concerns about their…
Adversarial training is an approach of increasing the robustness of models to adversarial attacks by including adversarial examples in the training set. One major challenge of producing adversarial examples is to contain sufficient…
Overconfidence and underconfidence in machine learning classifiers is measured by calibration: the degree to which the probabilities predicted for each class match the accuracy of the classifier on that prediction. How one measures…
In safety-critical applications data-driven models must not only be accurate but also provide reliable uncertainty estimates. This property, commonly referred to as calibration, is essential for risk-aware decision-making. In regression a…
Many machine learning algorithms are vulnerable to almost imperceptible perturbations of their inputs. So far it was unclear how much risk adversarial perturbations carry for the safety of real-world machine learning applications because…
Reliable confidence estimation for the predictions is important in many safety-critical applications. However, modern deep neural networks are often overconfident for their incorrect predictions. Recently, many calibration methods have been…
Deep learning models achieve remarkable accuracy in computer vision tasks, yet remain vulnerable to adversarial examples--carefully crafted perturbations to input images that can deceive these models into making confident but incorrect…
Ensuring safety alignment is a critical requirement for large language models (LLMs), particularly given increasing deployment in real-world applications. Despite considerable advancements, LLMs remain susceptible to jailbreak attacks,…
The vulnerability of machine learning models to membership inference attacks has received much attention in recent years. However, existing attacks mostly remain impractical due to having high false positive rates, where non-member samples…
Confidence calibration is a major concern when applying artificial neural networks in safety-critical applications. Since most research in this area has focused on classification in the past, confidence calibration in the scope of object…
Despite the recent advances in a wide spectrum of applications, machine learning models, especially deep neural networks, have been shown to be vulnerable to adversarial attacks. Attackers add carefully-crafted perturbations to input, where…
As large language models attract increasing attention and find widespread application, concurrent challenges of reliability also arise at the same time. Confidence calibration, an effective analysis method for gauging the reliability of…
Being cautious is crucial for enhancing the trustworthiness of machine learning systems integrated into decision-making pipelines. Although calibrated probabilities help in optimal decision-making, perfect calibration remains unattainable,…
Despite the great progress of neural network-based (NN-based) machinery fault diagnosis methods, their robustness has been largely neglected, for they can be easily fooled through adding imperceptible perturbation to the input. For fault…