Related papers: Efficient Black-Box Checking via Model Checking wi…

Conformal prediction (CP) provides a comprehensive framework to produce statistically rigorous uncertainty sets for black-box machine learning models. To further improve the efficiency of CP, conformal correction is proposed to fine-tune or…

Verification of real-time systems involving hard timing constraints and concurrency is of utmost importance. Parametric timed model checking allows for formal verification in the presence of unknown timing constants or uncertainty (e.g.…

Recently, interpretable machine learning has re-explored concept bottleneck models (CBM). An advantage of this model class is the user's ability to intervene on predicted concept values, affecting the downstream output. In this work, we…

An important aspect of many particle accelerators is the constant evolution and frequent configuration changes that are needed to perform the experiments they are designed for. This often leads to the design of configurable software that…

Machine Reading Comprehension (MRC) reveals the ability to understand a given text passage and answer questions based on it. Existing research works in MRC rely heavily on large-size models and corpus to improve the performance evaluated by…

MATLAB/Simulink is the leading tool for simulating complex Cyber-Physical Systems (CPSs). The simulation models of complex CPSs are typically compute intensive, and the execution of test cases is long. Furthermore, the execution of test…

The goal of selective prediction is to allow an a model to abstain when it may not be able to deliver a reliable prediction, which is important in safety-critical contexts. Existing approaches to selective prediction typically require…

While vehicles have primarily been controlled through mechanical means in years past, an increasing number of embedded control systems are being installed and used, keeping pace with advances in electronic control technology and…

Model checking is a widespread automatic formal analysis that has been successful in discovering flaws in security protocols. However existing possibilities for state space explosion still hinder analyses of complex protocols and protocol…

Parameter-efficient fine-tuning (PEFT) methods have provided an effective way for adapting large vision-language models to specific tasks or scenarios. Typically, they learn a very small scale of parameters for pre-trained models in a…

The software development process for embedded systems is getting faster and faster, which generally incurs an increase in the associated complexity. As a consequence, consumer electronics companies usually invest a lot of resources in fast…

This document briefly describes the Black-Box Multi-Objective Optimization Benchmarking (BMOBench) platform. It presents the test problems, evaluation procedure, and experimental setup. To this end, the BMOBench is demonstrated by comparing…

In science and medicine, model interpretations may be reported as discoveries of natural phenomena or used to guide patient treatments. In such high-stakes tasks, false discoveries may lead investigators astray. These applications would…

Search-based software testing (SBST) of Simulink models helps find scenarios that demonstrate that the system can reach a state that violates one of its requirements. However, many SBST techniques for Simulink models rely on requirements…

Statistical Model Checking (SMC) is a trade-off between testing and formal verification. The core idea of the approach is to conduct some simulations of the system and verify if they satisfy some given property. In this paper we show that…

Mid-circuit measurements (MCMs) are crucial ingredients in the development of fault-tolerant quantum computation. While there have been rapid experimental progresses in realizing MCMs, a systematic method for characterizing noisy MCMs is…

Black-Box attacks on machine learning models occur when an attacker, despite having no access to the inner workings of a model, can successfully craft an attack by means of model theft. The attacker will train an own substitute model that…

Faced with distribution shift between training and test set, we wish to detect and quantify the shift, and to correct our classifiers without test set labels. Motivated by medical diagnosis, where diseases (targets) cause symptoms…

The growing complexity of Cyber-Physical Systems (CPS) and challenges in ensuring safety and security have led to the increasing use of deep learning methods for accurate and scalable anomaly detection. However, machine learning (ML) models…

Scenario-based virtual testing is one of the most significant methods to test and evaluate the safety of automated driving systems (ADSs). However, it is impractical to enumerate all concrete scenarios in a logical scenario space and test…