English
Related papers

Related papers: A Formal Verification Approach to Safeguard Contro…

200 papers

Deep reinforcement learning (DRL) is a powerful machine learning paradigm for generating agents that control autonomous systems. However, the ``black box'' nature of DRL agents limits their deployment in real-world safety-critical…

Estimation of an unknown deterministic vector from quantized sensor data is considered in the presence of spoofing attacks which alter the data presented to several sensors. Contrary to previous work, a generalized attack model is employed…

Information Theory · Computer Science 2016-12-21 Jiangfan Zhang , Rick S. Blum , Lance Kaplan , Xuanxuan Lu

Modern nonlinear control theory seeks to endow systems with properties such as stability and safety, and has been deployed successfully across various domains. Despite this success, model uncertainty remains a significant challenge in…

Systems and Control · Electrical Eng. & Systems 2021-04-02 Andrew J. Taylor , Victor D. Dorobantu , Sarah Dean , Benjamin Recht , Yisong Yue , Aaron D. Ames

``Vibe coding'' -- the practice of developing software through iteratively conversing with a large language model (LLM) -- has exploded in popularity within the last year. However, developers report key limitations including the…

Software Engineering · Computer Science 2025-11-04 Jacqueline Mitchell , Yasser Shaaban

Safety is the major consideration in controlling complex dynamical systems using reinforcement learning (RL), where the safety certificate can provide provable safety guarantee. A valid safety certificate is an energy function indicating…

Machine Learning · Computer Science 2022-05-27 Haitong Ma , Changliu Liu , Shengbo Eben Li , Sifa Zheng , Jianyu Chen

Given measurements from sensors and a set of standard forces, an optimization based approach to identify weakness in structures is introduced. The key novelty lies in letting the load and measurements to be random variables. Subsequently…

Optimization and Control · Mathematics 2023-11-22 Facundo N. Airaudo , Harbir Antil , Rainald Löhner , Umarkhon Rakhimov

Noisy data, non-convex objectives, model misspecification, and numerical instability can all cause undesired behaviors in machine learning systems. As a result, detecting actual implementation errors can be extremely difficult. We…

Software Engineering · Computer Science 2017-06-28 Daniel Selsam , Percy Liang , David L. Dill

Cross-validation (CV) is known to provide asymptotically exact tests and confidence intervals for model improvement but only when the model comparison is relatively stable. Surprisingly, we prove that even simple, individually stable models…

Machine Learning · Statistics 2026-02-10 Alexandre Bayle , Lucas Janson , Lester Mackey

Like any digital certificate, Verifiable Credentials (VCs) require a way to revoke them in case of an error or key compromise. Existing solutions for VC revocation, most prominently Bitstring Status List, are not viable for many use cases…

Cryptography and Security · Computer Science 2025-09-19 Felix Hoops , Jonas Gebele , Florian Matthes

When deploying machine learning models in high-stakes robotics applications, the ability to detect unsafe situations is crucial. Early warning systems can provide alerts when an unsafe situation is imminent (in the absence of corrective…

In this paper we propose a novel methodology that allows to design, in a purely data-based fashion and for linear single-input and single-output systems, both robustly stable and performing control systems for tracking piecewise constant…

Systems and Control · Electrical Eng. & Systems 2023-01-18 William D'Amico , Marcello Farina

Multifidelity modeling has been steadily gaining attention as a tool to address the problem of exorbitant model evaluation costs that makes the estimation of failure probabilities a significant computational challenge for complex real-world…

Methodology · Statistics 2024-11-26 Promit Chakroborty , Somayajulu L. N. Dhulipala , Michael D. Shields

Providing guarantees on the safe operation of robots against edge cases is challenging as testing methods such as traditional Monte-Carlo require too many samples to provide reasonable statistics. Built upon recent advancements in…

Robotics · Computer Science 2023-05-01 Guy Scher , Sadra Sadraddini , Ariel Yadin , Hadas Kress-Gazit

Preventing vulnerability exploits is a critical software maintenance task, and software engineers often rely on Common Vulnerability and Exposure (CVEs) reports for information about vulnerable systems and libraries. These reports include…

Software Engineering · Computer Science 2019-10-01 Danielle Gonzalez , Holly Hastings , Mehdi Mirakhorli

Estimating and detecting faults is crucial in ensuring safe and efficient automated systems. In the presence of disturbances, noise or varying system dynamics, such estimation is even more challenging. To address this challenge, this…

Optimization and Control · Mathematics 2021-12-13 Chris van der Ploeg , Emilia Silvas , Nathan van de Wouw , Peyman Mohajerin Esfahani

Runtime misconfiguration can lead to software performance degradation and even cause failure. Developers typically perform sanity checks during the configuration parsing stage to prevent invalid parameter values. However, we discovered that…

Software Engineering · Computer Science 2025-04-01 Chaopeng Luo , Yuanliang Zhang , Haochen He , Zhouyang Jia , Teng Wang , Shulin Zhou , Si Zheng , Shanshan Li

Cyber-Physical Systems (CPSs), comprising both software and physical components, arise in many industry-relevant domains and are often mission- or safety-critical. System-Level Verification (SLV) of CPSs aims at certifying that given (e.g.,…

Software Engineering · Computer Science 2023-07-31 Toni Mancini , Igor Melatti , Enrico Tronci

Modern automotive software is highly complex and consists of millions lines of code. For safety-relevant automotive software, it is recommended to use sound static program analysis to prove the absence of runtime errors. However, the…

Software Engineering · Computer Science 2023-10-26 Jesko Hecking-Harbusch , Jochen Quante , Maximilian Schlund

In this paper a class of single machine scheduling problems is considered. It is assumed that job processing times and due dates can be uncertain and they are specified in the form of discrete scenario set. A probability distribution in the…

Data Structures and Algorithms · Computer Science 2017-12-12 Adam Kasperski , Pawel Zielinski

Neural network verifiers aim to provide formal guarantees on model behavior, but existing verification benchmarks are fundamentally limited by their lack of ground-truth labels. As a result, verifier evaluation relies on indirect…

Machine Learning · Computer Science 2026-05-19 David Troxell , Yulia Alexandr , Sofia Hunt , Stephanie Lei , Guido Montúfar