Related papers: On the Reliability and Stability of Selective Meth…

Sample average approximation (SAA), a popular method for tractably solving stochastic optimization problems, enjoys strong asymptotic performance guarantees in settings with independent training samples. However, these guarantees are not…

YARA rules are widely shared across threat intelligence communities to enable collective defence against malware. This practice implicitly assumes that removing metadata (e.g., author fields) sufficiently protects the identity of…

Reliable confidence estimation is a challenging yet fundamental requirement in many risk-sensitive applications. However, modern deep neural networks are often overconfident for their incorrect predictions, i.e., misclassified samples from…

The impressive growth of smartphone devices in combination with the rising ubiquity of using mobile platforms for sensitive applications such as Internet banking, have triggered a rapid increase in mobile malware. In recent literature, many…

The use of tiered warnings and multicategorical forecasts are ubiquitous in meteorological operations. Here, a flexible family of scoring functions is presented for evaluating the performance of ordered multicategorical forecasts. Each…

Quantum key distribution (QKD) security fundamentally relies on the ability to distinguish genuine quantum correlations from classical eavesdropper simulations, yet existing certification methods lack rigorous statistical guarantees under…

Malicious software is an integral part of cybercrime defense. Due to the growing number of malicious attacks and their target sources, detecting and preventing the attack becomes more challenging due to the assault's changing behavior. The…

Vision-Language-Action (VLA) models enable general-purpose robotic policies by mapping visual observations and language instructions to low-level actions, but they often lack reliable introspection. A common practice is to compute a…

Malware often uses obfuscation techniques or is modified slightly to evade signature detection from antivirus software and malware analysis tools. Traditionally, to determine if a file is malicious and identify what type of malware a sample…

Machine learning algorithms are known to be susceptible to data poisoning attacks, where an adversary manipulates the training data to degrade performance of the resulting classifier. In this work, we present a unifying view of randomized…

As the use of machine learning in high impact domains becomes widespread, the importance of evaluating safety has increased. An important aspect of this is evaluating how robust a model is to changes in setting or population, which…

Grey failures in the computing continuum produce ambiguous overlapping symptoms that existing approaches fail to diagnose reliably, either due to a lack of causal awareness or acting under high epistemic uncertainty, risking destructive…

Background: Symbolic models, particularly decision trees, are widely used in software engineering for explainable analytics in defect prediction, configuration tuning, and software quality assessment. Most of these models rely on…

Validation accuracy is a necessary, but not sufficient, measure of a neural network classifier's quality. High validation accuracy during development does not guarantee that a model is free of serious flaws, such as vulnerability to…

Deep learning has emerged as a powerful approach for malware detection, demonstrating impressive accuracy across various data representations. However, these models face critical limitations in real-world, non-stationary environments where…

Deploying machine learning models in safety-critical domains poses a key challenge: ensuring reliable model performance on downstream user data without access to ground truth labels for direct validation. We propose the suitability filter,…

Applying Artificial Intelligence (AI) and Machine Learning (ML) in critical contexts, such as medicine, requires the implementation of safety measures to reduce risks of harm in case of prediction errors. Spotting ML failures is of…

Instruction tuned reasoning models are increasingly deployed with safety classifiers trained on frozen embeddings, assuming representation stability across model updates. We systematically investigate this assumption and find it fails:…

Genre identification is a subclass of non-topical text classification. The main difference between this task and topical classification is that genres, unlike topics, usually do not correspond to simple keywords, and thus they need to be…

Binary verification plays a pivotal role in software security, yet building a verification service that is both open and trustworthy poses a formidable challenge. In this paper, we introduce a novel binary verification service, AGORA,…