Papers

Adversarial Robustness Improvement for Deep Neural Networks

Charis Eleftheriadis, Andreas Symeonidis, and Panagiotis Katsaros

Preprint accepted with revision in Machine Vision and Applications

DOI

Mining Hyperproperties using Temporal Logic

Ezio Bartocci, Cristinel Mateis, Eleonora Nesterini, Nickovic, Dejan

ACM Transactions on Embedded Computing Systems
Volume 22, Issue 5, Article No. 156

DOI | Paper

Provable Correct and Adaptive Simplex Architecture for Bounded-Liveness Properties

Maderbacher, B., Schupp, S., Bartocci, E., Bloem, R., Ničković, D. and Könighofer, B.

SPIN’23 proceedings

DOI | Paper

Mining Specification Parameters for Multi-Class Classification

Ezio Bartocci, Cristinel Mateis, Eleonora Nesterini, and Dejan Nickovic

Proceedings of RV 2023 – 23rd International Conference, RV 2023, Thessaloniki, Greece, October 3–6, 2023

DOI | Paper

Structural Coding: A Low-Cost Scheme to Protect CNNs from Large-Granularity Memory Faults

Ali Asgari Khoshouyeh, Florian Geissler, Seyed Qutub, Michael Paulitsch, Prashant Nair, Karthik Pattabiraman

SC 23 – The International Conference for High Performance Computing, Networking, Storage, and Analysis

DOI | Paper

OpenSBT: A Modular Framework for Search-based Testing of Automated Driving Systems

Lev Sorokin, Tiziano Munaro, Damir Safin, Brian Hsuan-Cheng Liao, Adam Molin

DOI | Paper

Simulation-based Safety Assurance for an AVP System incorporating Learning-Enabled Components

Hasan Esen, Brian Hsuan-Cheng Liao

10th International Symposium on Development Methodology

DOI | Paper

Large-Scale Application of Fault Injection into PyTorch Models — an Extension to PyTorchFI for Validation Efficiency

Ralf Gräfe, Qutub Syed Sha, Florian Geissler, Michael Paulitsch

2023 53rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks – Supplemental Volume (DSN-S). Proceedings of DSN 2023 Industry track

DOI | Paper

A Low-Cost Strategic Monitoring Approach for Scalable and Interpretable Error Detection in Deep Neural Networks

Florian Geissler, Syed Qutub, Michael Paulitsch, and Karthik Pattabiraman

SafeComp 2023 proceedings

DOI | Paper

A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation

Xiaowei Huang, Wenjie Ruan, Wei Huang, Gaojie Jin, Yi Dong, Changshun Wu, Saddek Bensalem, Ronghui Mu, Yi Qi, Xingyu Zhao, Kaiwen Cai, Yanghao Zhang, Sihao Wu, Peipei Xu, Dengyu Wu, Andre Freitas, Mustafa A. Mustafa

DOI | Paper

Learning from Demonstrations of Critical Driving Behaviours Using Driver’s Risk Field

Yurui Du, Flavia Sofia Acerbo, Jens Kober, Tong Duy Son

IFAC World Congress 2023

DOI | Paper

Reinforcement Learning from Simulation to Real World Autonomous Driving using Digital Twin

Kevin L. Voogd, Jean-Pierre Allamaa, Javier Alonso-Mora, Son Tong

IFAC World Congress 2023

DOI | Paper

Formal XAI via Syntax-Guided Synthesis

Bjørner, Katrine; Judson, Samuel; Cano, Filip; Goldman, Drew; Shoemaker, Nick; Piskac, Ruzica; Könighofer, Bettina

AISoLA 2023 proceedings

DOI | Paper

Improving the Safety of 3D Object Detectors in Autonomous Driving using IoGT and Distance Measures

Hsuan-Cheng Liao, Chih-Hong Cheng, Hasan Esen, Alois Knoll

DOI | Paper

Are Transformers More Robust? Towards Exact Robustness Verification for Transformers

Hsuan-Cheng Liao, Chih-Hong Cheng, Hasan Esen, Alois Knoll

SafeComp 2023 proceedings

DOI | Paper

Attribute Repair for Threat Prevention

Tarrach Thorsten; Ebrahimi Masoud; König Sandra; Schmittner Christoph; Bloem Roderick; Nickovic Dejan

SafeComp 2023 proceedings

DOI | Paper

Hierarchical Distribution-Aware Testing of Deep Learning

Wei Huang, Xingyu Zhao, ALEC BANKS, VICTORIA COX, Xiaowei Huang

Journal ACM transactions on Software Engineering Methods

DOI | Paper

The Unnecessity of Assuming Statistically Independent Tests in Bayesian Software Reliability Assessments

Kizito Salako; Xingyu Zhao

IEEE Transactions on Software Engineering

DOI | Paper

Analyzing Intentional Behavior in Autonomous Agents Under Uncertainty

Filip Cano Córdoba, Samuel Judson, Timos Antonopoulos, Katrine Bjorner, Nicholas Shoemaker, Scott Shapiro, Ruzica Piskac, Bettina Könighofer

Proceedings of the IJCAI 2023 – 32nd International Joint Conference on Artificial Intelligence

DOI | Paper

Safety Shielding under Delayed Observation

Filip Cano, Alexander Palmisano, Martin Fraenzle, Roderick Bloem and Bettina Koenighofer

ICAPS 2023 – 33rd International Conference on Automated Planning and Scheduling

DOI | Paper

Reflections on Surrogate-Assisted Search-Based Testing: A Taxonomy and Two Replication Studies based on Industrial ADAS and Simulink Models

Shiva Nejati, Lev Sorokin, Damir Safin, Federico Formica, Mohammad Mahdi Mahboob, Claudio Menghi

Information and Software Technology Journal

DOI | Paper

Online Shielding for Reinforcement Learning

Bettina Könighofer; Julian Rudolf; Alexander Palmisano; Martin Tappler; Roderick Bloem

Innovations in Systems and Software Engineering

DOI | Paper

Towards a Digital Twin Architecture with Formal Analysis Capabilities for Learning-Enabled Autonomous Systems

Anastasios Temperekidis, Nikolaos Kekatos, Panagiotis Katsaros, Weicheng He, Saddek Bensalem, Hisham AbdElSabour, Mohamed AbdElsalam, Ashraf Salem

MESAS 2022 – 9th International Conference on Modelling and Simulation for Autonomous Systems

DOI | Paper

Formal Specification for Learning-Enabled Autonomous Systems

Saddek Bensalem, Chih-Hong Cheng, Xiaowei Huang, Panagiotis Katsaros, Adam Molin, Dejan Nickovic, Doron Peled

Software Verification and Formal Methods for ML-Enabled Autonomous Systems

DOI | Paper

Specification-guided critical scenario identification for automated driving

Adam Molin, Edgar A. Aguilar, Dejan Nickovic, Mengjia Zhu, Alberto Bemporad, and Hasan Esen

FM 2023 –  25th International Symposium on Formal Methods

DOI | Paper

Automata Learning meets Shielding

Martin Tappler, Stefan Pranger, Bettina Könighofer, Edi Muškardin, Roderick Bloem, Kim Larsen

ISoLA 2022 – 11th International Symposium On Leveraging Applications of Formal Methods, Verification and Validation Principles

DOI | Paper

Reliable Multimodal Trajectory Prediction via Error Aligned Uncertainty Optimization

Neslihan Kose Cihangir, Ranganath Krishnan, Akash Dhamasia, Omesh Tickoo, Michael Paulitsch

SAIAD 2022 – 4th Workshop Safe Artificial Intelligence for Automated Driving in conjunction with ECCV 2022.

DOI | Paper

Runtime Verification for FMI-Based Co-simulation

Anastasios Temperekidis, Nikolaos Kekatos, and Panagiotis Katsaros

Runtime Verification. RV 2022. Lecture Notes in Computer Science, vol 13498

DOIPaper

On Neural Network Equivalence Checking using SMT Solvers

Charis Eleftheriadis, Nikolaos Kekatos, Panagiotis Katsaros, and Stavros Tripakis

Formal Modeling and Analysis of Timed Systems. FORMATS 2022. Lecture Notes in Computer Science

DOIPaper

Survey on mining signal temporal logic specifications

Ezio Bartocci; Cristinel Mateis; Eleonora Nesterini; Dejan Nickovic

Information and Computation journal

DOIPaper

DeepSTL – From English Requirements to Signal Temporal Logic

Jie He, Ezio Bartocci, Dejan Nickovic and Radu Grosu

ICSE ’22: Proceedings of the 44th International Conference on Software Engineering

DOIPaper

Enhancing Adversarial Training with Second-Order Statistics of Weights

Gaojie Jin, Xinping Yi, Liang Zhang, Lijun Zhang, Sven Schewe, Xiaowei Huang

CVPR 2022 – 2022 Conference on Computer Vision and Pattern Recognition

Paper

A Hierarchical HAZOP-Like Safety Analysis for Learning-Enable Systems

Yi Qi, Philippa Ryan, Wei Huang, Xingyu Zhao and Xiaowei Huang

AISafety 2022 workshop  at IJCAI2022

DOIPaper

Strategies for MDP Bisimilarity Equivalence and Inequivalence

Stefan Kiefer, Qiyi Tang

Concur 2022 –  33RD INTERNATIONAL CONFERENCE ON CONCURRENCY THEORY

DOIPaper

Hidden 1-Counter Markov Models and How to Learn Them

Mehmet Kurucan, Mete Ozbaltan, Sven Schewe, Dominik Wojtczak

IJCAI 2022 – 31st International Joint Conference on Artificial Intelligence

DOIPaper

Search-Based Testing of Reinforcement Learning

Martin Tappler, Filip Cano Cordoba, Bernhard Aichernig, Bettina Könighofer

Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence (IJCAI 2022) Main Track.

DOIPaper

Semantic Modeling and Analysis of Natural Language System Requirements

Konstantinos Mokos, Theodoros Nestoridis, Panagiotis Katsaros, Nick Bassiliades

IEEE Access Journal

DOIPaper

Hardware Faults that Matter: Understanding and Estimating the Safety Impact of Hardware Faults on Object Detection DNNs

Syed Qutub, Florian Geissler, Yang Peng, Ralf Gräfe, Michael Paulitsch, Gereon Hinz, and Alois Knoll

Safecomp 2022

DOIPaper

Robustness Verification for Attention Networks using Mixed Integer Programming

Hsuan-Cheng Liao, Chih-Hong Cheng, Maximilian Kneissl, Alois Knoll

DOIPaper

Virtual Reality Assisted Human Perception in ADAS Development: a Munich 3D Model Study

Felix Bognar, Oster Markus, Herman Van der Auweraer, Tong Duy Son

DOIPaper

Deciding What is Good-for-MDPs
Sven Schewe, Qiyi Tang and Tansholpan Zhanabekova

DOIPaper

Towards Trustworthy Camera-Based Sensing and Perception Systems
Christian Berghoff, Jona Böddinghaus, Vasilios Danos, Gabrielle Davelaar, Thomas Doms, Heiko Ehrich, Alexandru Forrai, Radu Grosu, Ronan Hamon, Henrik Junklewitz, Matthias Neu, Simon Romanski, Wojciech Samek, Dirk Schlesinger, Jan-Eve Stavesand, Sebastian Steinbach, Arndt von Twickel, Robert Walter, Johannes Weissenböck, Markus Wenzel, Thomas Wiegand

Whitepaper | May 2022. Towards Auditable AI Systems. From Principles to Practice.  Based on the 2nd international Workshop “Towards Auditable AI Systems”, October 26th 2021, Fraunhofer Forum Digitale Technologien, Berlin, organized by the Federal Office for Information Security Germany, the TÜV-Verband and the Fraunhofer HHI

DOIPaper

Information-flow Interfaces
Ezio Bartocci, Thomas Ferrère, Thomas A. Henzinger, Dejan Nickovic & Ana Oliveira da Costa

Fundamental Approaches to Software Engineering. FASE 2022. Lecture Notes in Computer Science, vol 13241.

DOIPaper

Adversarial Robustness of Deep Learning: Theory, Algorithms, and Applications
Wenjie Ruan; Xinping Yi; Xiaowei Huang

CIKM ’21: The 30th ACM International Conference on Information and Knowledge Management

DOIPaper

Dependability Analysis of Deep Reinforcement Learning based Robotics and Autonomous Systems
Dong, Yi; Zhao, Xingyu; Huang, Xiaowei

arxiv

Detecting Operational Adversarial Examples for Reliable Deep Learning
Zhao, Xingyu; Huang, Wei; Schewe, Sven; Dong, Yi; Huang, Xiaowei;

51ST ANNUAL IEEE/IFIP INTERNATIONAL CONFERENCE ON DEPENDABLE SYSTEMS AND NETWORKS – SUPPLEMENTAL VOL (DSN 2021)

DOI Paper

Model-Free Reinforcement Learning for Lexicographic ω-Regular Objectives
Ernst Moritz Hahn, Mateo Perez, Sven Schewe, Fabio Somenzi, Ashutosh Trivedi, and Dominik Wojtczak

24th International Symposium, FM 2021

DOI Paper

TEMPEST – Synthesis Tool for Reactive Systems and Shields in Probabilistic Environments
Stefan Pranger; Bettina Könighofer; Lukas Posch; Roderick Bloem

ATVA 2021

DOI Paper

Mining Shape Expressions with ShapeIt
Ezio Bartocci, Jyotirmoy Deshmukh, Cristinel Mateis, Eleonora Nesterini, Dejan Nickovic, and Xin Qin

19th International Conference on Software Engineering and Formal Methods (SEFM’21)

DOI Paper

EPMC Gets Knowledge in Multi-Agent Systems
Chen Fu, Ernst Moritz Hahn, Yong Li, Sven Schewe, Meng Sun, Andrea Turrini, and Lijun Zhang

VMCAI 2022 – 23rd International Conference on Verification, Model Checking, and Abstract Interpretation

DOI Paper

Continuous Safety Verification of Neural Networks
Chih-Hong Cheng, Rongjie Yan

Design, Automation & Test in Europe Conference & Exhibition (DATE) 2021

DOI Paper

Provably-Robust Runtime Monitoring of Neuron Activation Patterns
Chih-Hong Cheng

Design, Automation & Test in Europe Conference & Exhibition (DATE) 2021

DOI Paper

Safe Imitation Learning on Real-Life Highway Data for Human-like Autonomous Driving
Flavia Sofia Acerbo, Mohsen Alirezaei, Herman Van der Auweraer, Tong Duy Son.

24th IEEE International Conference on Intelligent Transportation – ITSC2021

arxiv

Coverage Guided Testing for Recurrent Neural Networks
Wei Huang, Youcheng Sun, Xingyu Zhao, James Sharp, Wenjie Ruan, Jie Meng, and Xiaowei Huang

IEEE Transactions on Reliability,

DOI Paper

Testing Autonomous Systems with Believed Equivalence Refinement
Chih-Hong Cheng, Rongjie Yan

IEEE International Conference On Artificial Intelligence Testing (AITest) 2021

DOI Paper

Assessing the reliability of deep learning classifiers through robustness evaluation and operational profiles
Zhao, X., Huang, W., Banks, A., Cox, V., Flynn, D., Schewe, S., and Huang, X.

AISafety’21 Workshop at IJCAI’21

Paper

BayLIME: Bayesian Local Interpretable Model-Agnostic Explanations
Xingyu Zhao, Xiaowei Huang, et. Al.

UAI2021 Proceedings of Machine Learning Research (PMLR)

Published Version | arxiv

Monitoring Object Detection Abnormalities via Data-Label and Post-Algorithm Abstractions
Yuhang Chen, Chih-Hong Cheng, Jun Yan and Rongjie Yan

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2021)

arxiv

Safety and Reliability of Deep Learning (Brief Overview)
Xiaowei Huang

Workshop: Verification of Autonomous & Robotic Systems (VARS) 2021

DOI | Paper

Safe, Deterministic Trajectory Planning for Unstructured and Partially Occluded Environments
Sebastian vom Dorff, Maximilian Kneissl, Martin Fränzle

ITSC2021 – 24th IEEE International Conference on Intelligent Transportation

arxiv

Safety Metrics for Semantic Segmentation in Autonomous Driving
Chih-Hong Cheng, Alois Knoll, and Hsuan-Cheng Liao

IEEE International Conference On Artificial Intelligence Testing, (AI Test 2021)

DOI Paper

Embedding and Extraction of Knowledge in Tree Ensemble Classifiers
Xingyu Zhao, Xiaowei Huang

Machine Learning journal (Springer)

arxiv

Sampling of Shape Expressions with ShapEx
Nicolas Basset; Thao Dang; Felix Gigler; Cristinel Mateis; Dejan Nickovic

MEMOCODE 2021 – 19th ACM-IEEE International Conference on Formal Methods and Models for System Design

Paper

Real-time Nonlinear MPC Strategy with Full Vehicle Validation for Autonomous Driving
Jean Pierre Allamaa, Petr Listov, Herman Van der Auweraer, Colin Jones, Tong Duy Son

MEMOCODE 2021 – 19th ACM-IEEE International Conference on Formal Methods and Models for System Design

arxiv

How does Weight Correlation Affect Generalisation Ability of Deep Neural Networks?
Gaojie Jin, Xinping Yi, Liang Zhang, Lijun Zhang, Sven Schewe, Xiaowei Huang

34th Conference on Neural Information Processing Systems (NeurIPS 2020)

arxiv