From FUnction-based TO MOdel-based automated probabilistic reasoning for DEep Learning

Weighted Automata Extraction and Explanation of Recurrent Neural Networks for Natural Language Tasks

Autores: Zeming Wei, Xiyue Zhang, Yihao Zhang, Meng Sun
Publicado en: Journal of Logical and Algebraic Methods in Programming, Edición Volume 136, January 2024, 100907, 2023, ISSN 2352-2208
Editor: ELSEVIER
DOI: 10.1016/j.jlamp.2023.100907

Planning for Automated Vehicles with Human Trust

Autores: Shili Sheng, Erfan Pakdamanian, Kyungtae Han, Ziran Wang, John Lenneman, David Parker, Lu Feng
Publicado en: ACM Transactions on Cyber-Physical Systems, 2022, ISSN 2378-962X
Editor: Association for Computing Machinery
DOI: 10.1145/3561059

Automated Verification of Concurrent Stochastic Systems

Autores: Marta Kwiatkowska, Gethin Norman, David Parker, Gabriel Santos
Publicado en: Formal Methods in System Design, 2021, ISSN 0925-9856
Editor: Kluwer Academic Publishers
DOI: 10.1007/s10703-020-00356-y

Evaluation and learning in two-player symmetric games via best and better response

Autores: Rui Yan, Weixian Zhang, Ruiliang Deng, Xiaoming Duan, Zongying Shi, Yisheng Zhong
Publicado en: Information Sciences, 2023, ISSN 0020-0255
Editor: Elsevier BV
DOI: 10.1016/j.ins.2023.119459

Physiologically-Informed Gaussian Processes for Interpretable Modelling of Psycho-Physiological States

Autores: Shadi Ghiasi, Andrea Patane, Luca Laurenti, Claudio Gentili, Enzo Pasquale Scilingo, Alberto Greco, Marta Kwiatkowska
Publicado en: EEE Journal of Biomedical and Health Informatics (J-BHI), 2022, ISSN 2168-2194
Editor: Institute of Electrical and Electronics Engineers Inc.

Multiplayer Homicidal Chauffeur Reach-Avoid Games: A Pursuit Enclosure Function Approach

Autores: Rui Yan, Xiaoming Duan, Rui Zou, Xin He, Zongying Shi, Francesco Bullo
Publicado en: Automatica, 2024, ISSN 1873-2836
Editor: Elsevier
DOI: 10.48550/arxiv.2311.02389

PREMAP: A Unifying PREiMage APproximation Framework for Neural Networks

Autores: Xiyue Zhang, Benjie Wang, Marta Kwiatkowska, Huan Zhang
Publicado en: Journal of Machine Learning Research (JMLR), 2025, ISSN 1533-7928
Editor: JMLR
DOI: 10.48550/arxiv.2408.09262

Online control synthesis for uncertain systems under signal temporal logic specifications

Autores: Pian Yu, Yulong Gao, Frank J. Jiang, Karl H. Johansson and Dimos V. Dimarogonas
Publicado en: International Journal of Robotics Research, 2023, ISSN 0278-3649
Editor: SAGE Publications
DOI: 10.1177/02783649231212572

A Language for Modeling and Optimizing Experimental Biological Protocols

Autores: Luca Cardelli; Marta Kwiatkowska; Luca Laurenti
Publicado en: Computation, Edición 9, 107, 2021, ISSN 2079-3197
Editor: MDPI
DOI: 10.3390/computation9100107

On the Hardness of Robust Classification

Autores: Pascale Gourdeau, Varun Kanade, Marta Kwiatkowska and James Worrell
Publicado en: Journal of Machine Learning Research, 2021, ISSN 1532-4435
Editor: MIT Press

Probabilistic Reach-Avoid for Bayesian Neural Networks

Autores: Wicker, Matthew; Laurenti, Luca; Patane, Andrea; Paoletti, Nicola; Abate, Alessandro; Kwiatkowska, Marta
Publicado en: Artificial Intelligence, Edición 8, 2024, ISSN 0004-3702
Editor: Elsevier BV
DOI: 10.48550/arxiv.2310.01951

Probabilistic model checking and autonomy

Autores: Marta Kwiatkowska, Gethin Norman and David Parker
Publicado en: Annual Review of Control, Robotics, and Autonomous Systems, Edición 5:1,, 2022, Página(s) 385-410, ISSN 2573-5144
Editor: Annual Review of Control, Robotics, and Autonomous Systems
DOI: 10.1146/annurev-control-042820-010947

Adversarial Robustness Guarantees for Gaussian Processes

Autores: Andrea Patane, Arno Blaas, Luca Laurenti, Luca Cardelli, Stephen Roberts, Marta Kwiatkowska
Publicado en: Journal of Machine Learning Research, Edición 23(146), 2022, Página(s) 1−55, ISSN 2640-3498
Editor: PMLR

Robust Control for Dynamical Systems with Non-Gaussian Noise via Formal Abstractions.

Autores: Thom Badings, Licio Romao, Alessandro Abate, David Parker, Hasan A. Poonawala, Marielle Stoelinga and Nils Jansen.
Publicado en: Journal of Artificial Intelligence Research, Edición 76, 2023, ISSN 1076-9757
Editor: Morgan Kaufmann Publishers, Inc.
DOI: 10.1613/jair.1.14253

Strategy Synthesis for Zero-Sum Neuro-Symbolic Concurrent Stochastic Games

Autores: Rui Yan, Gabriel Santos, Gethin Norman, David Parker, Marta Kwiatkowska
Publicado en: Information and Computation, 2024, Página(s) 105193, ISSN 0890-5401
Editor: Academic Press
DOI: 10.1016/j.ic.2024.105193

A Framework for Simultaneous Task Allocation and Planning under Uncertainty

Autores: Fatma Faruq, Bruno Lacerda, Nick Hawes, David Parker
Publicado en: ACM Transactions on Autonomous and Adaptive Systems, 2024, ISSN 1556-4703
Editor: Association for Computing Machinery
DOI: 10.1145/3665499

Rational verification: game-theoretic verification of multi-agent systems

Autores: Abate, Alessandro; Gutierrez, Julian; Hammond, Lewis; Harrenstein, Paul; Kwiatkowska, Marta; Najib, Muhammad; Perelli, Giuseppe; Steeples, Thomas; Wooldridge, Michael
Publicado en: Applied Intelligence, Edición 51, 2021, Página(s) 6569–6584, ISSN 0924-669X
Editor: Kluwer Academic Publishers
DOI: 10.1007/s10489-021-02658-y

On the Role of Explainability and Uncertainty in Ensuring Safety of AI Applications

Autores: Rhiannon Falconmore
Publicado en: PhD thesis, 2022
Editor: University of Oxford

Automatic Verification and Strategy Synthesis for Zero-sum and Equilibria Properties of Concurrent Stochastic Games

Autores: Gabriel Santos
Publicado en: PhD thesis, 2021
Editor: University of Oxford

Formal Verification of Deep Reinforcement Learning Agents

Autores: Edoardo Bacci
Publicado en: PhD thesis, 2022
Editor: University of Birmingham

Sample complexity of robust learning against evasion attacks

Autores: Pascale Gourdeau
Publicado en: PhD thesis, 2023
Editor: University of Oxford

Tractable probabilistic models for causal learning and reasoning

Autores: Benjie Wang
Publicado en: PhD thesis, 2023
Editor: University of Oxford
DOI: 10.5287/ora-2anj4dbdx

Modelling Human-Like Decision Making and Social Trust Using Probabilistic Programming

Autores: Maciej Olejnik
Publicado en: PhD thesis, 2022
Editor: University of Oxford

On the Adversarial Robustness of Gaussian Processes

Autores: Andrea Patane
Publicado en: PhD thesis, 2021
Editor: University of Oxford

Robustness Evaluation of Deep Neural Networks with Provable Guarantees

Autores: Min Wu
Publicado en: PhD thesis, 2020
Editor: University of Oxford

On Robustness for Natural Language Processing

Autores: Emanuele La Malfa
Publicado en: PhD thesis, 2023
Editor: University of Oxford
DOI: 10.5287/ora-2a4grvayz

Adversarial robustness of Bayesian neural networks

Autores: Matthew Wicker
Publicado en: PhD thesis, 2022
Editor: University of Oxford

PRISM 4.8

Autores: David Parker, Gethin Norman, Marta Kwiatkowska
Publicado en: Software, 2023
Editor: n/a

On the Benefits of Invariance in Neural Networks

Autores: Clare Lyle, Mark van der Wilk, Marta Kwiatkowska, Yarin Gal, Benjamin Bloem-Reddy
Publicado en: Technical report Presented as poster at the NeurIPS 2019 Machine Learning with Guarantees Workshop., 2020
Editor: Machine Learning
DOI: 10.48550/arxiv.2005.00178

Emergent Linguistic Structures in Neural Networks are Fragile

Autores: Emanuele La Malfa, Matthew Wicker, Marta Kwiatkowska
Publicado en: Technical report, 2023
Editor: arxiv
DOI: 10.48550/arxiv.2210.17406

PREMAP

Autores: Xiyue Zhang
Publicado en: Software, 2025
Editor: n/a

Model-Based Diagnosis with Multiple Observations: A Unified Approach for C Software and Boolean Circuits

Autores: Pedro Orvalho, Marta Kwiatkowska, Mikoláš Janota, Vasco Manquinho
Publicado en: 2025
Editor: arxiv

Bayesian Network Models of Causal Interventions in Healthcare Decision Making: Literature Review and Software Evaluation

Autores: Artem Velikzhanin, Benjie Wang, Marta Kwiatkowska
Publicado en: Technical report, under submission, 2022
Editor: Department of Computer Science University of Oxford
DOI: 10.48550/arxiv.2211.15258

Robustness of Unsupervised Representation Learning without Labels

Autores: Aleksandar Petrov, Marta Kwiatkowska
Publicado en: Technical report, under submission, 2022
Editor: online

PRISM-games 3.0 and 3.1

Autores: Marta Kwiatkowska, Gethin Norman, David Parker, Gabriel Santos
Publicado en: Software, 2020
Editor: n/a

DeepBayes

Autores: Matthew Wicker
Publicado en: Software, 2022
Editor: n/a

Point-based Value Iteration for Neuro-Symbolic POMDPs

Autores: Rui Yan, Gabriel Santos, Gethin Norman, David Parker, Marta Kwiatkowska
Publicado en: Technical report, under submission, 2023
Editor: Technical report arXiv:2306.17639, arXiv.
DOI: 10.48550/arxiv.2306.17639

SafeDRL

Autores: David Parker
Publicado en: Software, 2022
Editor: n/a

PRISM-games 3.2

Autores: David Parker, Gethin Norman, Marta Kwiatkowska
Publicado en: Software, 2023
Editor: n/a

Uncertainty-Aware Explanations Through Probabilistic Self-Explainable Neural Networks

Autores: Jon Vadillo, Roberto Santana, Jose A. Lozano, Marta Kwiatkowska
Publicado en: Technical report, under submission, 2024
Editor: TBC
DOI: 10.48550/arxiv.2403.13740

Uncertify: Attacks Against Neural Network Certification

Autores: Lorenz, Tobias; Kwiatkowska, Marta; Fritz, Mario
Publicado en: Technical report, under submission, Edición 1, 2021
Editor: Technical report - Under submission
DOI: 10.48550/arxiv.2108.11299

Double Machine Learning for Conditional Moment Restrictions: IV regression, Proximal Causal Learning and Beyond

Autores: Daqian Shao, Ashkan Soleymani, Francesco Quinzan, Marta Kwiatkowska
Publicado en: 2025
Editor: TBC
DOI: 10.48550/arxiv.2506.14950focustolearnmore

PRISM 4.7

Autores: David Parker, Gethin Norman, Marta Kwiatkowska
Publicado en: Software, 2021
Editor: n/a

PRISM 4.9

Autores: David Parker
Publicado en: Software, 2025
Editor: n/a

Human-in-the-Loop Oversight of AI is Compromised by Political Preferences

Autores: Terence Daniel Dores Cruz, Christopher Starke, Tim Katzke, Emmanuel Müller, Marta Kwiatkowska, Orly Lobel, Nils Köbis and Shaul Shalvi
Publicado en: 2025
Editor: PsyArXiv

Exact Verification of Graph Neural Networks with Incremental Constraint Solving

Autores: Minghao Liu, Chia-Hsuan Lu, Marta Kwiatkowska
Publicado en: 2025
Editor: TBC - Technical paper under submission
DOI: 10.48550/arxiv.2508.09320

STR-Cert: Robustness Certification for Deep Text Recognition on Deep Learning Pipelines and Vision Transformers

Autores: Daqian Shao, Lukas Fesser, Marta Kwiatkowska
Publicado en: Technical report, under submission, 2024
Editor: Technical report, under submission
DOI: 10.48550/arxiv.2401.05338

Learning Algorithms for Verification of Markov Decision Processes

Autores: Tomáš Brázdil, Krishnendu Chatterjee, Martin Chmelik, Vojtěch Forejt, Jan Křetínský, Marta Kwiatkowska, Tobias Meggendorfer, David Parker, Mateusz Ujma
Publicado en: Technical report, under submission, 2024
Editor: TBC

PRISM-games 3.2.1

Autores: David Parker
Publicado en: Software, 2025
Editor: n/a

Efficient Preimage Approximation for Neural Network Certification

Autores: Anton Björklund, Mykola Zaitsev, Marta Kwiatkowska
Publicado en: Technical paper, under submission, 2025
Editor: TBC
DOI: 10.48550/arxiv.2505.22798

Are Large Language Models Robust in UnderstandingCode Against Semantics-Preserving Mutations?

Autores: Pedro Orvalho, Marta Kwiatkowska
Publicado en: Technical paper under submission, 2025
Editor: TBC
DOI: 10.48550/arxiv.2505.10443

webppl-cognitive-agents

Autores: Maciej Olejnik
Publicado en: Software and data, 2022
Editor: n/a

PyVeritas: On Verifying Python via LLM-Based Transpilation and Bounded Model Checking for C

Autores: Pedro Orvalho, Marta Kwiatkowska
Publicado en: 2025
Editor: Technical report, pending to be accepted

The Complexity of Learning Temporal Properties

Autores: Benjamin Bordais, Daniel Neider, Rajarshi Roy
Publicado en: 42nd International Symposium on Theoretical Aspects of Computer Science (STACS 2025), 2025
Editor: TBC

Bayesian Inference with Certifiable Adversarial Robustness

Autores: Matthew Wicker, Luca Laurenti, Andrea Patane, Zhuotong Chen, Zheng Zhang, Marta Kwiatkowska
Publicado en: Proceedings, International Conference on Artificial Intelligence and Statistics (AISTATS'21), 2021
Editor: PMLR

Safe POMDP Online Planning via Shielding

Autores: Shili Sheng, David Parker, Lu Feng
Publicado en: In Proc. IEEE International Conference on Robotics and Automation (ICRA'24), 2024
Editor: The final version is forthcoming from IEEE.
DOI: 10.48550/arxiv.2309.10216

Learning Provably Robust Policies in Uncertain Parametric Environments

Autores: Yannik Schnitzer, Alessandro Abate, David Parker
Publicado en: In Proc. 31st International Conference on Tools and Algorithms for the Construction and Analysis of Systems (TACAS'25), 2025
Editor: Springer Nature

Multi-Objective Controller Synthesis with Uncertain Human Preferences

Autores: Shenghui Chen, Kayla Boggess, David Parker, Lu Feng
Publicado en: Proc. ACM/IEEE 13th International Conference on Cyber-Physical Systems (ICCPS'22), 2022
Editor: ACM/IEEE International Conference on Cyber-Physical Systems
DOI: 10.48550/arxiv.2105.04662

Distributional Probabilistic Model Checking

Autores: Ingy Elsayed-Aly, David Parker, Lu Feng
Publicado en: In Proc. 16th International Symposium NASA Formal Methods (NFM'24), 2024, ISSN 0302-9743
Editor: Springer
DOI: 10.48550/arxiv.2309.05584

Learning Decision Policies with Instrumental Variables through Double Machine Learning.

Autores: Daqian Shao, Ashkan Soleymani, Francesco Quinzan, Marta Kwiatkowska
Publicado en: 41st. International Conference on Machine Learning (ICML 2024), 2024
Editor: TBC
DOI: 10.48550/arxiv.2405.08498

Learning Probabilistic Temporal Logic Specifications for Stochastic Systems

Autores: Rajarshi Roy, Yash Pote, David Parker, Marta Kwiatkowska
Publicado en: Proceedings of IJCAI-25, 2025
Editor: IJCAI-25

Sampling-Based Robust Control of Autonomous Systems with Non-Gaussian Noise

Autores: Thom S. Badings, Alessandro Abate, Nils Jansen, David Parker, Hasan A. Poonawala, Marielle Stoelinga
Publicado en: Proc. 36th AAAI Conference on Artificial Intelligence (AAAI'22), 2022
Editor: AAAI Press
DOI: 10.48550/arxiv.2110.12662

Strategyproof Reinforcement Learning from Human Feedback

Autores: Thomas Kleine Buening, Jiarui Gan, Debmalya Mandal, Marta Kwiatkowska
Publicado en: Proc. 39th Annual Conference on Neural Information Processing Systems (NeurIPS'25), 2025
Editor: NeurIPS
DOI: 10.48550/arxiv.2503.09561focustolearnmore

The King is Naked: on the Notion of Robustness for Natural Language Processing

Autores: Emanuele La Malfa, Marta Kwiatkowska
Publicado en: Proc. 36th AAAI Conference on Artificial Intelligence (AAAI'22), 2022
Editor: Association for the Advancement of Artificial Intelligence
DOI: 10.48550/arxiv.2112.07605

Compositional Probabilistic and Causal Inference using Tractable Circuit Models

Autores: Benjie Wang, Marta Kwiatkowska
Publicado en: 26th International Conference on Artificial Intelligence and Statistics, AISTATS'23, Edición 206, 2023, Página(s) 9488-9498, ISSN 2640-3498
Editor: Journal of Machine Learning Research
DOI: 10.48550/arxiv.2304.08278

FAST: Boosting Uncertainty-based Test Prioritization Methods for Neural Networks via Feature Selection

Autores: Jialuo Chen, Jingyi Wang, Xiyue Zhang, Youcheng Sun, Marta Kwiatkowska, Jiming Chen, Peng Cheng
Publicado en: 39th IEEE/ACM International Conference on Automated Software Engineering (ASE 2024), 2024, Página(s) https://conf.researchr.org/home/ase-2024
Editor: TBC
DOI: 10.48550/arxiv.2409.09130

Robustness Guarantees for Bayesian Neural Networks (invited extended abstract of a keynote speaker)

Autores: Marta Kwiatkowska
Publicado en: In Proc. 19th International Conference on Quantitative Evaluation of SysTems (QEST 2022), 2022
Editor: Springer

A Unifying Framework for Causal Imitation Learningwith Hidden Confounders

Autores: Daqian Shao, Thomas Kleine Buening, Marta Kwiatkowska.
Publicado en: Workshop on Spurious Correlation and Shortcut Learning: Foundations and Solutions, Workshop at The International Conference on Learning Representations (ICLR) 2025, 2025
Editor: OpenReview
DOI: 10.48550/arxiv.2502.07656

FullCert: Deterministic End-to-End Certification for Training and Inference of Neural Networks

Autores: Tobias Lorenz, Marta Kwiatkowska, Mario Fritz
Publicado en: The German Conference on Pattern Recognition (GCPR), 2024, Página(s) https://www.gcpr-vmv.de/year/2024
Editor: Springer Nature
DOI: 10.48550/arxiv.2406.11522

Planning with Linear Temporal Logic Specifications: Handling Quantifiable and Unquantifiable Uncertainty

Autores: Pian Yu, Yong Li, David Parker, Marta Kwiatkowska
Publicado en: Proc. at IEEE International Conference on Robotics and Automation (ICRA), 2025
Editor: TBC

Provable Preimage Under-Approximation for Neural Networks

Autores: Zhang, Xiyue; Wang, Benjie; Kwiatkowska, Marta
Publicado en: TACAS 2024, 30th International Conference on Tools and Algorithms for the Construction and Analysis of Systems, Edición 30, 2024, ISSN 0302-9743
Editor: Springer
DOI: 10.48550/arxiv.2305.03686

What Is Formal Verification Without Specifications? A Survey on Mining LTL Specifications

Autores: Daniel Neider, Rajarshi Roy
Publicado en: In: Jansen, N., et al. Principles of Verification: Cycling the Probabilistic Landscape . Lecture Notes in Computer Science, vol 15262, 2024
Editor: Springer
DOI: 10.48550/arxiv.2501.16274

Safe POMDP Online Planning among Dynamic Agents via Adaptive Conformal Prediction

Autores: Shili Sheng, Pian Yu, David Parker, Marta Kwiatkowska and Lu Feng
Publicado en: The IEEE Robotics and Automation Letters (RA-L), 2024
Editor: The IEEE Robotics and Automation Letters (RA-L)
DOI: 10.48550/arxiv.2404.15557

When to trust AI: advances and challenges for certification of neural networks

Autores: Marta Kwiatkowska, Xiyue Zhang
Publicado en: Proceedings of the 18th Conference on Computer Science and Intelligence Systems (FedCSIS 2023), 2023
Editor: IEEE

Symbolic Causal Inference via Operations on Probabilistic Circuits

Autores: Benjie Wang, Marta Kwiatkowska
Publicado en: NeurIPS Workshop on Neuro Causal and Symbolic AI (nCSI), 2022
Editor: NeurIPS

Robustness Guarantees for Credal Bayesian Networks via Constraint Relaxation over Probabilistic Circuits.

Autores: Hjalmar Wijk, Benjie Wang, Marta Kwiatkowska
Publicado en: Proc. 31st International Joint Conference on Artificial Intelligence (IJCAI'22), 2022
Editor: International Joint Conferences on Artificial Intelligence
DOI: 10.48550/arxiv.2205.05793

Robust Decision Pipelines: Opportunities and Challenges for AI in Business Process Modelling

Autores: Marta Kwiatkowska
Publicado en: BPM 2023 Forum, Utrecht, The Netherlands, 2023
Editor: A Springer Nature Computer Science book series.

Adversarial Robustness Certification for Bayesian Neural Networks

Autores: Matthew Wicker, Andrea Patane, Luca Laurenti, Marta Kwiatkowska
Publicado en: 6th International Symposium on Formal Methods (FM'24 invited paper), 2024
Editor: Springer
DOI: 10.48550/arxiv.2306.13614

Individual Fairness Guarantees for Neural Networks

Autores: Elias Benussi, Andrea Patane, Matthew Wicker, Luca Laurenti, Marta Kwiatkowska
Publicado en: Proc. 31st International Joint Conference on Artificial Intelligence (IJCAI'22), 2022
Editor: International Joint Conferences on Artificial Intelligence
DOI: 10.48550/arxiv.2205.05763

Expectation vs. Reality: Towards Verification of Psychological Games

Autores: Marta Kwiatkowska, Gethin Norman, David Parker and Gabriel Santos
Publicado en: In Jansen, N., et al., Principles of Verification: Cycling the Probabilistic Landscape, volume 15262 of LNCS, 2024, Página(s) 126–154
Editor: Springer
DOI: 10.1007/978-3-031-75783-9

Certification of Iterative Predictions in Bayesian Neural Networks

Autores: Matthew Wicker, Luca Laurenti, Andrea Patane, Nicola Paoletti, Alessandro Abate, Marta Kwiatkowska
Publicado en: 37th Conference on Uncertainty in Artificial Intelligence (UAI'21), 2021
Editor: Association for Uncertainty in Artificial Intelligence (AUAI)

Safety and Robustness for Deep Learning with Provable Guarantees

Autores: Marta Kwiatkowska
Publicado en: Proceedings, 35th IEEE/ACM International Conference on Automated Software Engineering (ASE ’20), 2020
Editor: ACM

Counterexample Guided Program Repair Using Zero-Shot Learning and MaxSAT-based Fault Localization

Autores: Pedro Orvalho, Mikola´s Janota, Vasco Manquinho
Publicado en: Proc. Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI-25), 2024
Editor: TBC
DOI: 10.48550/arxiv.2502.07786

Sample Efficient Model-free Reinforcement Learning from LTL Specifications with Optimality Guarantees

Autores: Daqian Shao, Marta Kwiatkowska
Publicado en: 32nd International Joint Conference on Artificial Intelligence (IJCAI 2023), Edición n/a, 2023
Editor: IJCAI
DOI: 10.24963/ijcai.2023/465

Sample complexity bounds for robustly learning decision lists against evasion attacks

Autores: Pascale Gourdeau, Varun Kanade, Marta Kwiatkowska and James Worrell
Publicado en: Proc. 31st International Joint Conference on Artificial Intelligence (IJCAI'22), 2022
Editor: International Joint Conferences on Artificial Intelligence
DOI: 10.48550/arxiv.2205.06127

HSVI-based Online Minimax Strategies for Partially Observable Stochastic Games with Neural Perception Mechanisms

Autores: Rui Yan, Gabriel Santos, Gethin Norman, David Parker, Marta Kwiatkowska
Publicado en: Proc. 6th Annual Learning for Dynamics & Control Conference, L4DC 2024, 2024
Editor: 6th Annual Learning for Dynamics & Control Conference, L4DC 2024
DOI: 10.48550/arxiv.2404.10679focustolearnmore

Probabilistic Model Checking for Strategic Equilibria-based Decision Making: Advances and Challenges.

Autores: Marta Kwiatkowska, Gethin Norman, David Parker, Gabriel Santos, Rui Yan
Publicado en: In Proc. 47th International Symposium on Mathematical Foundations of Computer Science (MFCS'22)., Edición 241 (4), 2022
Editor: Schloss Dagstuhl - Leibniz-Zentrum für Informatik
DOI: 10.4230/lipics.mfcs.2022.4

Verified Probabilistic Policies for Deep Reinforcement Learning

Autores: Edoardo Bacci, David Parker
Publicado en: International Symposium NASA Formal Methods (NFM'22)., 2022
Editor: Springer
DOI: 10.48550/arxiv.2201.03698

When are Local Queries Useful for Robust Learning?https://papers.nips.cc/paper_files/paper/2022/hash/db6461eaf0eaeaad1d9c4a70e4818cbd-Abstract-Conference.html

Autores: Pascale Gourdeau, Varun Kanade, Marta Kwiatkowska, James Worrell
Publicado en: NeurIPS 2022, 2022
Editor: NeurIPS paper

Finite-horizon Equilibria for Neuro-symbolic Concurrent Stochastic Games

Autores: Rui Yan, Gabriel Santos, Xiaoming Duan, David Parker, Marta Kwiatkowska
Publicado en: Proc. 38th Conference on Uncertainty in Artificial Intelligence (UAI'22), 2022
Editor: AUAI Press

Certifiers Make Neural Networks Vulnerable to Availability Attacks

Autores: Tobias Lorenz, Marta Kwiatkowska and Mario Fritz
Publicado en: 16th ACM Workshop on Artificial Intelligence and Security (AISec 2023), 2023
Editor: AISec 2023

Probabilistic Guarantees for Safe Deep Reinforcement Learning

Autores: Edoardo Bacci, David Parker
Publicado en: Formal Modeling and Analysis of Timed Systems - 18th International Conference, FORMATS 2020, Vienna, Austria, September 1–3, 2020, Proceedings, Edición 12288, 2020, Página(s) 231-248, ISBN 978-3-030-57627-1
Editor: Springer International Publishing
DOI: 10.1007/978-3-030-57628-8_14

DRCFS: Doubly Robust Causal Feature Selection

Autores: Francesco Quinzan, Ashkan Soleymani, Patrik Jaillet, Cristian R. Rojas, Stefan Bauer
Publicado en: Fortieth International Conference on Machine Learning, ICML 2023, 2023
Editor: ICML 2023

Multi-player Equilibria Verification for Concurrent Stochastic Games

Autores: Marta Kwiatkowska, Gethin Norman, David Parker, Gabriel Santos
Publicado en: Proc. 17th International Conference on Quantitative Evaluation of SysTems (QEST'20), 2020
Editor: Springer

On Correctness, Precision, and Performance in Quantitative Verification: QComp 2020 Competition Report

Autores: Carlos E. Budde, Arnd Hartmanns, Michaela Klauck, Jan Kretinsky, David Parker, Tim Quatmann, Andrea Turrini and Zhen Zhang
Publicado en: Proc. 9th International Symposium on Leveraging Applications of Formal Methods, Verification and Validation (ISoLA'20), 2020
Editor: Springer

Automated Design of Linear Bounding Functions for Sigmoidal Nonlinearities in Neural Networks

Autores: Matthias König, Xiyue Zhang, Holger H. Hoos, Marta Kwiatkowska, Jan N. van Rijn
Publicado en: ECML-PKDD 2024- European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD) 2024, 2024
Editor: TBC
DOI: 10.48550/arxiv.2406.10154

Robust anytime learning of Markov decision processes

Autores: Marnix Suilen, Thiago D. Simão, Nils Jansen, David Parker
Publicado en: In Proc. 36th Annual Conference on Neural Information Processing Systems (NeurIPS'22), 2022
Editor: NeurIPS 2022
DOI: 10.48550/arxiv.2205.15827

MIBP-Cert: Certified Training against Data Perturbations with Mixed-Integer Bilinear Programs.

Autores: Tobias Lorenz, Marta Kwiatkowska and Mario Fritz
Publicado en: Proc. 39th Annual Conference on Neural Information Processing Systems (NeurIPS'25), 2025
Editor: Curran Associates

Provable Guarantees on the Robustness of Decision Rules to Causal Interventions

Autores: Benjie Wang, Clare Lyle, Marta Kwiatkowska
Publicado en: 30th International Joint Conference on Artificial Intelligence (IJCAI'21), 2021
Editor: IJCAI

Tractable Uncertainty for Structure Learning

Autores: Benjie Wang, Matthew Wicker, Marta Kwiatkowska
Publicado en: Proc. 39th International Conference on Machine Learning (ICML'22), 2022
Editor: PMLR

The Trembling-Hand Problem for LTLf Planning

Autores: Pian Yu, Shufang Zhu, Giuseppe De Giacomo, Marta Kwiatkowska, Moshe Vardi
Publicado en: 33rd International Joint Conference on Artificial Intelligence (IJCAI 2024), 2024
Editor: IJCAI 2024/TBC
DOI: 10.48550/arxiv.2404.16163

Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models

Autores: Hannah Rose Kirk, yennie jun, Filippo Volpin, Haider Iqbal, Elias Benussi, Frederic Dreyer, Aleksandar Shtedritski, Yuki Asano
Publicado en: Advances in Neural Information Processing Systems 34 (NeurIPS 2021), 2021
Editor: PMLR

Safety Verification for Deep Neural Networks with Provable Guarantees (Invited Paper)

Autores: Marta Kwiatkowska
Publicado en: 30th International Conference on Concurrency Theory (CONCUR 2019), 2019
Editor: Schloss Dagstuhl--Leibniz-Zentrum fuer Informatik
DOI: 10.4230/lipics.concur.2019.1

Safety Guarantees for Iterative Predictions with Gaussian Processes

Autores: Kyriakos Polymenakos, Luca Laurenti, Andrea Patane, Jan-Peter Calliess, Luca Cardelli, Marta Kwiatkowska, Alessandro Abate, Stephen Roberts
Publicado en: Proceedings, 59th IEEE Conference on Decision and Control (CDC), 2020
Editor: IEEE

Robust Markov Decision Processes: A Place Where AI and Formal Methods Meet

Autores: Marnix Suilen, Thom Badings, Eline M. Bovy, David Parker, Nils Jansen
Publicado en: In Jansen, N., et al., Principles of Verification: Cycling the Probabilistic Landscape, volume 15262 of LNCS, 2024, Página(s) 126–154
Editor: Springer
DOI: 10.48550/arxiv.2411.11451

Efficient Solution and Learning of Robust Factored MDPs

Autores: Yannik Schnitzer, Alessandro Abate, David Parker
Publicado en: Proc. 40th AAAI Conference on Artificial Intelligence (AAAI'26), 2026
Editor: AAAI

Partially Observable Stochastic Games with Neural Perception Mechanisms

Autores: Rui Yan, Gabriel Santos, Gethin Norman, David Parker, Marta Kwiatkowska
Publicado en: In Proc. 26th International Symposium on Formal Methods (FM'24), 2024
Editor: Springer
DOI: 10.48550/arxiv.2310.11566

PRISM-games 3.0: Stochastic Game Verification with Concurrency, Equilibria and Time

Autores: Marta Kwiatkowska, Gethin Norman, David Parker, Gabriel Santos
Publicado en: Computer Aided Verification - 32nd International Conference, CAV 2020, Los Angeles, CA, USA, July 21–24, 2020, Proceedings, Part II, Edición 12225, 2020, Página(s) 475-487, ISBN 978-3-030-53290-1
Editor: Springer International Publishing
DOI: 10.1007/978-3-030-53291-8_25

Assessing Robustness of Text Classification through Maximal Safe Radius Computation

Autores: Emanuele La Malfa, Min Wu, Luca Laurenti, Benjie Wang, Anthony Hartshorn, Marta Kwiatkowska
Publicado en: Findings of the Association for Computational Linguistics: EMNLP 2020, 2020, Página(s) 2949-2968
Editor: Association for Computational Linguistics
DOI: 10.18653/v1/2020.findings-emnlp.266

Verifying Reinforcement Learning up to Infinity

Autores: Edoardo Bacci, Mirco Giacobbe, David Parker
Publicado en: Proceedings, 30th International Joint Conference on Artificial Intelligence (IJCAI-21), 2021
Editor: IJCAI

Multi-agent verification and control with probabilistic model checking

Autores: David Parker
Publicado en: Proc. 20th International Conference on Quantitative Evaluation of SysTems (QEST'23), 2023, Página(s) https://www.qest.org/qest2023/
Editor: Spinger
DOI: 10.48550/arxiv.2308.02829

Learning Dynamics and Generalization in Reinforcement Learning

Autores: Clare Lyle, Mark Rowland, Will Dabney, Marta Kwiatkowska, Yarin Gal
Publicado en: Proc. 39th International Conference on Machine Learning (ICML'22), 2022
Editor: PMLR

Correlated equilibria and fairness in concurrent stochastic games

Autores: Marta Kwiatkowska, Gethin Norman, David Parker, Gabriel Santos
Publicado en: Tools and Algorithms for the Construction and Analysis of Systems - 28th International Conference, TACAS 2022, 2022, ISSN 0302-9743
Editor: Springer

On Guaranteed Optimal Robust Explanations for NLP Models

Autores: Emanuele La Malfa, Agnieszka Zbrzezny, Rhiannon Michelmore, Nicola Paoletti, Marta Kwiatkowska
Publicado en: Proceedings, 30th International Joint Conference on Artificial Intelligence (IJCAI-21), 2021
Editor: IJCAI

Invariant Causal Prediction for Block MDPs

Autores: Amy Zhang, Clare Lyle, Shagun Sodhani, Angelos Filos, Marta Kwiatkowska, Joelle Pineau, Yarin Gal, Doina Precup
Publicado en: Proceedings of the 37th International Conference on Machine Learning (ICML), 2020
Editor: PMLR 119

Probabilistic Safety for Bayesian Neural Networks

Autores: Matthew Wicker, Luca Laurenti, Andrea Patane, Marta Kwiatkowska
Publicado en: Proceedings, 36th Conference on Uncertainty in Artificial Intelligence (UAI 2020), 2020
Editor: PMLR

Strategy Synthesis for Partially Observable Stochastic Games with Neural Perception Mechanisms

Autores: Marta Kwiatkowska
Publicado en: 32nd EACSL Annual Conference on Computer Science Logic (CSL 2024), 2024
Editor: Schloss Dagstuhl -- Leibniz-Zentrum fur Informatik
DOI: 10.4230/lipics.csl.2024.5

Tools at the Frontiers of Quantitative Verification

Autores: Roman Andriushchenko, Alexander Bork, Carlos E. Budde, Milan Češka, Kush Grover, Ernst Moritz Hahn, Arnd Hartmanns, Bryant Israelsen, Nils Jansen, Joshua Jeppson, Sebastian Junges, Maximilian A. Köhl, Bettina Könighofer, Jan Křetínský, Tobias Meggendorfer, David Parker, Stefan Pranger, Tim Quatmann, Enno Ruijters, Landon Taylor, Matthias Volk, Maximilian Weininger, Zhen Zhang
Publicado en: TOOLympics III, 2024
Editor: Springer
DOI: 10.48550/arxiv.2405.13583

Adversarial Robustness Guarantees for Classification with Gaussian Processes

Autores: Arno Blaas, Andrea Patane, Luca Laurenti, Luca Cardelli, Marta Kwiatkowska, Stephen Roberts
Publicado en: Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics (AISTATS 2020), 2020
Editor: PMLR
DOI: 10.48550/arxiv.1905.11876

Probabilistic Timed ATL

Autores: Wojciech Jamroga, Marta Kwiatkowska, Wojciech Penczek, Laure Petrucci, Teofil Sidoruk
Publicado en: 24th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2025, 2025
Editor: TBC

Reactive and human-in-the-loop planning and control of multi-robot systems under LTL specifications in dynamic environments

Autores: Pian Yu, Gianmarco Fedeli and Dimos V. Dimarogonas
Publicado en: 9th International Conference on Control, Decision and Information Technologies (CoDIT 2023), 2023
Editor: EEE Xplore
DOI: 10.48550/arxiv.2307.06000

Robustness Guarantees for Deep Neural Networks on Videos

Autores: Min Wu, Marta Kwiatkowska
Publicado en: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, Página(s) 308-317, ISBN 978-1-7281-7168-5
Editor: IEEE
DOI: 10.1109/cvpr42600.2020.00039

Tractable Uncertainty for Structure Learning

Autores: Benjie Wang, Matthew Wicker, Marta Kwiatkowska
Publicado en: In 5th Workshop on Tractable Probabilistic Modelling (TPM). This paper was accepted for ICML 2022, Edición 162, 2022, Página(s) 23131-23150
Editor: PMLR

Trust-Aware Motion Planning for Human-Robot Collaboration under Distribution Temporal Logic Specifications

Autores: Yu, Pian; Dong, Shuyang; Sheng, Shili; Feng, Lu; Kwiatkowska, Marta
Publicado en: 2024 IEEE International Conference on Robotics and Automation (ICRA2024), 2024
Editor: IEEE
DOI: 10.48550/arxiv.2310.01163

Probabilistic Model Checking: Applications and Trends

Autores: Marta Kwiatkowska, Gethin Norman, David Parker
Publicado en: Lecture Notes in Computer Science, Principles of Formal Quantitative Analysis, 2025, Página(s) 158-173
Editor: Springer Nature Switzerland
DOI: 10.1007/978-3-031-97439-7_7

Symbolic Verification and Strategy Synthesis for Turn-based Stochastic Games

Autores: Marta Kwiatkowska, Gethin Norman, David Parker, Gabriel Santos
Publicado en: Principles of Systems Design, Lecture Notes in Computer Science, 2022, Página(s) 9783031223365, ISBN 978-3-031-22336-5
Editor: Springer
DOI: 10.1007/978-3-031-22337-2_19

Publicaciones

Compartir esta página Compartir esta página en las redes sociales

Descargar Descargar el contenido de la página