Related papers: Adversarial Stress Tests for Quantum Certification

Conditional independence (CI) is central to causal inference, feature selection, and graphical modeling, yet it is untestable in many settings without additional assumptions. Existing CI tests often rely on restrictive structural…

Adaptiveness is a key principle in information processing including statistics and machine learning. We investigate the usefulness of adaptive methods in the framework of asymptotic binary hypothesis testing, when each hypothesis represents…

Due to the imbalanced and limited data, semi-supervised medical image segmentation methods often fail to produce superior performance for some specific tailed classes. Inadequate training for those particular classes could introduce more…

Measurement incompatibility underpins randomness generation in nonlocal phenomena. However, at its root, a more fundamental quantum feature is noncommuting (or coherent) measurements. This raises a central question: How can we operationally…

Adversarial training is well-known to produce high-quality neural network models that are empirically robust against adversarial perturbations. Nevertheless, once a model has been adversarially trained, one often desires a certification…

In this work, we present a novel machine learning framework called Self-Directed Task Identification (SDTI), which enables models to autonomously identify the correct target variable for each dataset in a zero-shot setting without…

A recent line of research on automated speaking assessment (ASA) has benefited from self-supervised learning (SSL) representations, which capture rich acoustic and linguistic patterns in non-native speech without underlying assumptions of…

Conformal prediction has emerged as an effective strategy for uncertainty quantification by modifying a model to output sets of labels instead of a single label. These prediction sets come with the guarantee that they contain the true label…

Pseudo-label based self training approaches are a popular method for source-free unsupervised domain adaptation. However, their efficacy depends on the quality of the labels generated by the source trained model. These labels may be…

Ordinal regression is aimed at predicting an ordinal class label. In this paper, we consider its semi-supervised formulation, in which we have unlabeled data along with ordinal-labeled data to train an ordinal regressor. There are several…

Semi-supervised learning (SSL) enables prediction with limited labels, but high-stakes tabular applications (medical, credit, recidivism) require statistical fairness guarantees. We identify a structural conflict in tabular fair SSL through…

Self-adaptive systems (SASs) are capable of adjusting its behavior in response to meaningful changes in the operational con-text and itself. The adaptation needs to be performed automatically through self-managed reactions and…

Machine learning models are vulnerable to adversarial attacks. One approach to addressing this vulnerability is certification, which focuses on models that are guaranteed to be robust for a given perturbation size. A drawback of recent…

Semi-Supervised Learning (SSL) can leverage abundant unlabeled data to boost model performance. However, the class-imbalanced data distribution in real-world scenarios poses great challenges to SSL, resulting in performance degradation.…

Test automation has become increasingly important as the complexity of both design and content in Human Machine Interface (HMI) software continues to grow. Current standard practice uses Optical Character Recognition (OCR) techniques to…

Randomness is fundamental for secure communication and information processing. While continuous-variable optical systems offer an attractive platform for this task, certifying genuine quantum randomness in such setups remains challenging.…

In recent years, a number of process-based anomaly detection schemes for Industrial Control Systems were proposed. In this work, we provide the first systematic analysis of such schemes, and introduce a taxonomy of properties that are…

We study the security of a quantum key distribution (QKD) protocol under the one-sided device-independent (1sDI) setting, which assumes trust in only one party's measurement device. This approach effectively provides a balance between the…

Object detectors encounter challenges in handling domain shifts. Cutting-edge domain adaptive object detection methods use the teacher-student framework and domain adversarial learning to generate domain-invariant pseudo-labels for…

We report an experimental certification of indefinite causal order that relies only on the characterization of the operations of a single party. We do so in the semi-device-independent scenario with the fewest possible assumptions of…