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

Autori: Zeming Wei, Xiyue Zhang, Yihao Zhang, Meng Sun
Pubblicato in: Journal of Logical and Algebraic Methods in Programming, Numero Volume 136, January 2024, 100907, 2023, ISSN 2352-2208
Editore: ELSEVIER
DOI: 10.1016/j.jlamp.2023.100907

Planning for Automated Vehicles with Human Trust

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

Automated Verification of Concurrent Stochastic Systems

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

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

Autori: Rui Yan, Weixian Zhang, Ruiliang Deng, Xiaoming Duan, Zongying Shi, Yisheng Zhong
Pubblicato in: Information Sciences, 2023, ISSN 0020-0255
Editore: Elsevier BV
DOI: 10.1016/j.ins.2023.119459

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

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

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

Autori: Rui Yan, Xiaoming Duan, Rui Zou, Xin He, Zongying Shi, Francesco Bullo
Pubblicato in: Automatica, 2024, ISSN 1873-2836
Editore: Elsevier
DOI: 10.48550/arxiv.2311.02389

PREMAP: A Unifying PREiMage APproximation Framework for Neural Networks

Autori: Xiyue Zhang, Benjie Wang, Marta Kwiatkowska, Huan Zhang
Pubblicato in: Journal of Machine Learning Research (JMLR), 2025, ISSN 1533-7928
Editore: JMLR
DOI: 10.48550/arxiv.2408.09262

Online control synthesis for uncertain systems under signal temporal logic specifications

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

A Language for Modeling and Optimizing Experimental Biological Protocols

Autori: Luca Cardelli; Marta Kwiatkowska; Luca Laurenti
Pubblicato in: Computation, Numero 9, 107, 2021, ISSN 2079-3197
Editore: MDPI
DOI: 10.3390/computation9100107

On the Hardness of Robust Classification

Autori: Pascale Gourdeau, Varun Kanade, Marta Kwiatkowska and James Worrell
Pubblicato in: Journal of Machine Learning Research, 2021, ISSN 1532-4435
Editore: MIT Press

Probabilistic Reach-Avoid for Bayesian Neural Networks

Autori: Wicker, Matthew; Laurenti, Luca; Patane, Andrea; Paoletti, Nicola; Abate, Alessandro; Kwiatkowska, Marta
Pubblicato in: Artificial Intelligence, Numero 8, 2024, ISSN 0004-3702
Editore: Elsevier BV
DOI: 10.48550/arxiv.2310.01951

Probabilistic model checking and autonomy

Autori: Marta Kwiatkowska, Gethin Norman and David Parker
Pubblicato in: Annual Review of Control, Robotics, and Autonomous Systems, Numero 5:1,, 2022, Pagina/e 385-410, ISSN 2573-5144
Editore: Annual Review of Control, Robotics, and Autonomous Systems
DOI: 10.1146/annurev-control-042820-010947

Adversarial Robustness Guarantees for Gaussian Processes

Autori: Andrea Patane, Arno Blaas, Luca Laurenti, Luca Cardelli, Stephen Roberts, Marta Kwiatkowska
Pubblicato in: Journal of Machine Learning Research, Numero 23(146), 2022, Pagina/e 1−55, ISSN 2640-3498
Editore: PMLR

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

Autori: Thom Badings, Licio Romao, Alessandro Abate, David Parker, Hasan A. Poonawala, Marielle Stoelinga and Nils Jansen.
Pubblicato in: Journal of Artificial Intelligence Research, Numero 76, 2023, ISSN 1076-9757
Editore: Morgan Kaufmann Publishers, Inc.
DOI: 10.1613/jair.1.14253

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

Autori: Rui Yan, Gabriel Santos, Gethin Norman, David Parker, Marta Kwiatkowska
Pubblicato in: Information and Computation, 2024, Pagina/e 105193, ISSN 0890-5401
Editore: Academic Press
DOI: 10.1016/j.ic.2024.105193

A Framework for Simultaneous Task Allocation and Planning under Uncertainty

Autori: Fatma Faruq, Bruno Lacerda, Nick Hawes, David Parker
Pubblicato in: ACM Transactions on Autonomous and Adaptive Systems, 2024, ISSN 1556-4703
Editore: Association for Computing Machinery
DOI: 10.1145/3665499

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

Autori: Abate, Alessandro; Gutierrez, Julian; Hammond, Lewis; Harrenstein, Paul; Kwiatkowska, Marta; Najib, Muhammad; Perelli, Giuseppe; Steeples, Thomas; Wooldridge, Michael
Pubblicato in: Applied Intelligence, Numero 51, 2021, Pagina/e 6569–6584, ISSN 0924-669X
Editore: Kluwer Academic Publishers
DOI: 10.1007/s10489-021-02658-y

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

Autori: Rhiannon Falconmore
Pubblicato in: PhD thesis, 2022
Editore: University of Oxford

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

Autori: Gabriel Santos
Pubblicato in: PhD thesis, 2021
Editore: University of Oxford

Formal Verification of Deep Reinforcement Learning Agents

Autori: Edoardo Bacci
Pubblicato in: PhD thesis, 2022
Editore: University of Birmingham

Sample complexity of robust learning against evasion attacks

Autori: Pascale Gourdeau
Pubblicato in: PhD thesis, 2023
Editore: University of Oxford

Tractable probabilistic models for causal learning and reasoning

Autori: Benjie Wang
Pubblicato in: PhD thesis, 2023
Editore: University of Oxford
DOI: 10.5287/ora-2anj4dbdx

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

Autori: Maciej Olejnik
Pubblicato in: PhD thesis, 2022
Editore: University of Oxford

On the Adversarial Robustness of Gaussian Processes

Autori: Andrea Patane
Pubblicato in: PhD thesis, 2021
Editore: University of Oxford

Robustness Evaluation of Deep Neural Networks with Provable Guarantees

Autori: Min Wu
Pubblicato in: PhD thesis, 2020
Editore: University of Oxford

On Robustness for Natural Language Processing

Autori: Emanuele La Malfa
Pubblicato in: PhD thesis, 2023
Editore: University of Oxford
DOI: 10.5287/ora-2a4grvayz

Adversarial robustness of Bayesian neural networks

Autori: Matthew Wicker
Pubblicato in: PhD thesis, 2022
Editore: University of Oxford

PRISM 4.8

Autori: David Parker, Gethin Norman, Marta Kwiatkowska
Pubblicato in: Software, 2023
Editore: n/a

On the Benefits of Invariance in Neural Networks

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

Emergent Linguistic Structures in Neural Networks are Fragile

Autori: Emanuele La Malfa, Matthew Wicker, Marta Kwiatkowska
Pubblicato in: Technical report, 2023
Editore: arxiv
DOI: 10.48550/arxiv.2210.17406

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

Autori: Artem Velikzhanin, Benjie Wang, Marta Kwiatkowska
Pubblicato in: Technical report, under submission, 2022
Editore: Department of Computer Science University of Oxford
DOI: 10.48550/arxiv.2211.15258

Strategyproof Reinforcement Learning from Human Feedback

Autori: Thomas Kleine Buening, Jiarui Gan, Debmalya Mandal, Marta Kwiatkowska
Pubblicato in: 2025
Editore: TBC -Technical paper under submission
DOI: 10.48550/arxiv.2503.09561focustolearnmore

Robustness of Unsupervised Representation Learning without Labels

Autori: Aleksandar Petrov, Marta Kwiatkowska
Pubblicato in: Technical report, under submission, 2022
Editore: online

PRISM-games 3.0 and 3.1

Autori: Marta Kwiatkowska, Gethin Norman, David Parker, Gabriel Santos
Pubblicato in: Software, 2020
Editore: n/a

DeepBayes

Autori: Matthew Wicker
Pubblicato in: Software, 2022
Editore: n/a

A Unifying Framework for Causal Imitation Learningwith Hidden Confounders

Autori: Daqian Shao, Thomas Kleine Buening, Marta Kwiatkowska.
Pubblicato in: Technical report, 2025
Editore: TBC

Point-based Value Iteration for Neuro-Symbolic POMDPs

Autori: Rui Yan, Gabriel Santos, Gethin Norman, David Parker, Marta Kwiatkowska
Pubblicato in: Technical report, under submission, 2023
Editore: Technical report arXiv:2306.17639, arXiv.
DOI: 10.48550/arxiv.2306.17639

SafeDRL

Autori: David Parker
Pubblicato in: Software, 2022
Editore: n/a

PRISM-games 3.2

Autori: David Parker, Gethin Norman, Marta Kwiatkowska
Pubblicato in: Software, 2023
Editore: n/a

Uncertainty-Aware Explanations Through Probabilistic Self-Explainable Neural Networks

Autori: Jon Vadillo, Roberto Santana, Jose A. Lozano, Marta Kwiatkowska
Pubblicato in: Technical report, under submission, 2024
Editore: TBC
DOI: 10.48550/arxiv.2403.13740

Uncertify: Attacks Against Neural Network Certification

Autori: Lorenz, Tobias; Kwiatkowska, Marta; Fritz, Mario
Pubblicato in: Technical report, under submission, Numero 1, 2021
Editore: Technical report - Under submission
DOI: 10.48550/arxiv.2108.11299

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

Autori: Daqian Shao, Ashkan Soleymani, Francesco Quinzan, Marta Kwiatkowska
Pubblicato in: 2025
Editore: TBC
DOI: 10.48550/arxiv.2506.14950focustolearnmore

PRISM 4.7

Autori: David Parker, Gethin Norman, Marta Kwiatkowska
Pubblicato in: Software, 2021
Editore: n/a

Exact Verification of Graph Neural Networks with Incremental Constraint Solving

Autori: Minghao Liu, Chia-Hsuan Lu, Marta Kwiatkowska
Pubblicato in: 2025
Editore: 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

Autori: Daqian Shao, Lukas Fesser, Marta Kwiatkowska
Pubblicato in: Technical report, under submission, 2024
Editore: Technical report, under submission
DOI: 10.48550/arxiv.2401.05338

Learning Algorithms for Verification of Markov Decision Processes

Autori: Tomáš Brázdil, Krishnendu Chatterjee, Martin Chmelik, Vojtěch Forejt, Jan Křetínský, Marta Kwiatkowska, Tobias Meggendorfer, David Parker, Mateusz Ujma
Pubblicato in: Technical report, under submission, 2024
Editore: TBC

Efficient Preimage Approximation for Neural Network Certification

Autori: Anton Björklund, Mykola Zaitsev, Marta Kwiatkowska
Pubblicato in: Technical paper, under submission, 2025
Editore: TBC
DOI: 10.48550/arxiv.2505.22798

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

Autori: Pedro Orvalhoa and Marta Kwiatkowska
Pubblicato in: Technical paper under submission, 2025
Editore: TBC
DOI: 10.48550/arxiv.2505.10443

webppl-cognitive-agents

Autori: Maciej Olejnik
Pubblicato in: Software and data, 2022
Editore: n/a

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

Autori: Pedro Orvalho, Marta Kwiatkowska
Pubblicato in: 2025
Editore: Technical report, pending to be accepted

The Complexity of Learning Temporal Properties

Autori: Benjamin Bordais, Daniel Neider, Rajarshi Roy
Pubblicato in: 42nd International Symposium on Theoretical Aspects of Computer Science (STACS 2025), 2025
Editore: TBC

Bayesian Inference with Certifiable Adversarial Robustness

Autori: Matthew Wicker, Luca Laurenti, Andrea Patane, Zhuotong Chen, Zheng Zhang, Marta Kwiatkowska
Pubblicato in: Proceedings, International Conference on Artificial Intelligence and Statistics (AISTATS'21), 2021
Editore: PMLR

Safe POMDP Online Planning via Shielding

Autori: Shili Sheng, David Parker and Lu Feng
Pubblicato in: In Proc. IEEE International Conference on Robotics and Automation (ICRA'24), 2024
Editore: The final version is forthcoming from IEEE.

Learning Provably Robust Policies in Uncertain Parametric Environments

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

Multi-Objective Controller Synthesis with Uncertain Human Preferences

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

Distributional Probabilistic Model Checking

Autori: Ingy Elsayed-Aly, David Parker and Lu Feng
Pubblicato in: In Proc. 16th International Symposium NASA Formal Methods (NFM'24), 2024
Editore: TBC

Learning Decision Policies with Instrumental Variables through Double Machine Learning.

Autori: Daqian Shao, Ashkan Soleymani, Francesco Quinzan, Marta Kwiatkowska
Pubblicato in: 41st. International Conference on Machine Learning (ICML 2024), 2024
Editore: TBC
DOI: 10.48550/arxiv.2405.08498

Learning Probabilistic Temporal Logic Specifications for Stochastic Systems

Autori: Rajarshi Roy, Yash Pote, David Parker, Marta Kwiatkowska
Pubblicato in: Proceedings of IJCAI-25, 2025
Editore: IJCAI-25

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

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

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

Autori: Emanuele La Malfa, Marta Kwiatkowska
Pubblicato in: Proc. 36th AAAI Conference on Artificial Intelligence (AAAI'22), 2022
Editore: Association for the Advancement of Artificial Intelligence
DOI: 10.48550/arxiv.2112.07605

Compositional Probabilistic and Causal Inference using Tractable Circuit Models

Autori: Benjie Wang and Marta Kwiatkowska
Pubblicato in: 26th International Conference on Artificial Intelligence and Statistics, AISTATS'23, Numero 206, 2023, Pagina/e 9488-9498, ISSN 2640-3498
Editore: Journal of Machine Learning Research
DOI: 10.48550/arxiv.2304.08278

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

Autori: Jialuo Chen, Jingyi Wang, Xiyue Zhang, Youcheng Sun, Marta Kwiatkowska, Jiming Chen, Peng Cheng
Pubblicato in: 39th IEEE/ACM International Conference on Automated Software Engineering (ASE 2024), 2024, Pagina/e https://conf.researchr.org/home/ase-2024
Editore: TBC
DOI: 10.48550/arxiv.2409.09130

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

Autori: Marta Kwiatkowska
Pubblicato in: In Proc. 19th International Conference on Quantitative Evaluation of SysTems (QEST 2022), 2022
Editore: Springer

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

Autori: Tobias Lorenz, Marta Kwiatkowska, Mario Fritz
Pubblicato in: The German Conference on Pattern Recognition (GCPR), 2024, Pagina/e https://www.gcpr-vmv.de/year/2024
Editore: Springer Nature
DOI: 10.48550/arxiv.2406.11522

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

Autori: Pian Yu, Yong Li, David Parker, Marta Kwiatkowska
Pubblicato in: Proc. at IEEE International Conference on Robotics and Automation (ICRA), 2025
Editore: TBC

Provable Preimage Under-Approximation for Neural Networks

Autori: Zhang, Xiyue; Wang, Benjie; Kwiatkowska, Marta
Pubblicato in: TACAS 2024, 30th International Conference on Tools and Algorithms for the Construction and Analysis of Systems, Numero 30, 2024, ISSN 0302-9743
Editore: Springer
DOI: 10.48550/arxiv.2305.03686

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

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

Safe POMDP Online Planning among Dynamic Agents via Adaptive Conformal Prediction

Autori: Shili Sheng, Pian Yu, David Parker, Marta Kwiatkowska and Lu Feng
Pubblicato in: The IEEE Robotics and Automation Letters (RA-L), 2024
Editore: 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

Autori: Marta Kwiatkowska, Xiyue Zhang
Pubblicato in: Proceedings of the 18th Conference on Computer Science and Intelligence Systems (FedCSIS 2023), 2023
Editore: IEEE

Symbolic Causal Inference via Operations on Probabilistic Circuits

Autori: Benjie Wang, Marta Kwiatkowska
Pubblicato in: NeurIPS Workshop on Neuro Causal and Symbolic AI (nCSI), 2022
Editore: NeurIPS

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

Autori: Hjalmar Wijk, Benjie Wang, Marta Kwiatkowska
Pubblicato in: Proc. 31st International Joint Conference on Artificial Intelligence (IJCAI'22), 2022
Editore: International Joint Conferences on Artificial Intelligence
DOI: 10.48550/arxiv.2205.05793

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

Autori: Marta Kwiatkowska
Pubblicato in: BPM 2023 Forum, Utrecht, The Netherlands, 2023
Editore: A Springer Nature Computer Science book series.

Adversarial Robustness Certification for Bayesian Neural Networks

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

Individual Fairness Guarantees for Neural Networks

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

Expectation vs. Reality: Towards Verification of Psychological Games

Autori: Marta Kwiatkowska, Gethin Norman, David Parker and Gabriel Santos
Pubblicato in: In Jansen, N., et al., Principles of Verification: Cycling the Probabilistic Landscape, volume 15262 of LNCS, 2024, Pagina/e 126–154
Editore: Springer
DOI: 10.1007/978-3-031-75783-9

Certification of Iterative Predictions in Bayesian Neural Networks

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

Safety and Robustness for Deep Learning with Provable Guarantees

Autori: Marta Kwiatkowska
Pubblicato in: Proceedings, 35th IEEE/ACM International Conference on Automated Software Engineering (ASE ’20), 2020
Editore: ACM

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

Autori: Pedro Orvalho, Mikola´s Janota, Vasco Manquinho
Pubblicato in: Proc. Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI-25), 2024
Editore: TBC
DOI: 10.48550/arxiv.2502.07786

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

Autori: Daqian Shao and Marta Kwiatkowska
Pubblicato in: 32nd International Joint Conference on Artificial Intelligence (IJCAI 2023), Numero n/a, 2023
Editore: IJCAI

Sample complexity bounds for robustly learning decision lists against evasion attacks

Autori: Pascale Gourdeau, Varun Kanade, Marta Kwiatkowska and James Worrell
Pubblicato in: Proc. 31st International Joint Conference on Artificial Intelligence (IJCAI'22), 2022
Editore: 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

Autori: Rui Yan, Gabriel Santos, Gethin Norman, David Parker, Marta Kwiatkowska
Pubblicato in: Proc. 6th Annual Learning for Dynamics & Control Conference, L4DC 2024, 2024
Editore: 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.

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

Verified Probabilistic Policies for Deep Reinforcement Learning

Autori: Edoardo Bacci, David Parker
Pubblicato in: International Symposium NASA Formal Methods (NFM'22)., 2022
Editore: 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

Autori: Pascale Gourdeau, Varun Kanade, Marta Kwiatkowska, James Worrell
Pubblicato in: NeurIPS 2022, 2022
Editore: NeurIPS paper

Finite-horizon Equilibria for Neuro-symbolic Concurrent Stochastic Games

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

Certifiers Make Neural Networks Vulnerable to Availability Attacks

Autori: Tobias Lorenz, Marta Kwiatkowska and Mario Fritz
Pubblicato in: 16th ACM Workshop on Artificial Intelligence and Security (AISec 2023), 2023
Editore: AISec 2023

Probabilistic Guarantees for Safe Deep Reinforcement Learning

Autori: Edoardo Bacci, David Parker
Pubblicato in: Formal Modeling and Analysis of Timed Systems - 18th International Conference, FORMATS 2020, Vienna, Austria, September 1–3, 2020, Proceedings, Numero 12288, 2020, Pagina/e 231-248, ISBN 978-3-030-57627-1
Editore: Springer International Publishing
DOI: 10.1007/978-3-030-57628-8_14

DRCFS: Doubly Robust Causal Feature Selection

Autori: Francesco Quinzan, Ashkan Soleymani, Patrik Jaillet, Cristian R. Rojas, Stefan Bauer
Pubblicato in: Fortieth International Conference on Machine Learning, ICML 2023, 2023
Editore: ICML 2023

Multi-player Equilibria Verification for Concurrent Stochastic Games

Autori: Marta Kwiatkowska, Gethin Norman, David Parker, Gabriel Santos
Pubblicato in: Proc. 17th International Conference on Quantitative Evaluation of SysTems (QEST'20), 2020
Editore: Springer

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

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

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

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

Robust anytime learning of Markov decision processes

Autori: Marnix Suilen, Thiago D. Simão, Nils Jansen, David Parker
Pubblicato in: In Proc. 36th Annual Conference on Neural Information Processing Systems (NeurIPS'22), 2022
Editore: NeurIPS 2022

Provable Guarantees on the Robustness of Decision Rules to Causal Interventions

Autori: Benjie Wang, Clare Lyle, Marta Kwiatkowska
Pubblicato in: 30th International Joint Conference on Artificial Intelligence (IJCAI'21), 2021
Editore: IJCAI

Tractable Uncertainty for Structure Learning

Autori: Benjie Wang, Matthew Wicker, Marta Kwiatkowska
Pubblicato in: Proc. 39th International Conference on Machine Learning (ICML'22), 2022
Editore: PMLR

The Trembling-Hand Problem for LTLf Planning

Autori: Pian Yu, Shufang Zhu, Giuseppe De Giacomo, Marta Kwiatkowska, Moshe Vardi
Pubblicato in: 33rd International Joint Conference on Artificial Intelligence (IJCAI 2024), 2024
Editore: 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

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

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

Autori: Marta Kwiatkowska
Pubblicato in: 30th International Conference on Concurrency Theory (CONCUR 2019), 2019
Editore: Schloss Dagstuhl--Leibniz-Zentrum fuer Informatik
DOI: 10.4230/lipics.concur.2019.1

Safety Guarantees for Iterative Predictions with Gaussian Processes

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

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

Autori: Marnix Suilen, Thom Badings, Eline M. Bovy, David Parker and Nils Jansen
Pubblicato in: In Jansen, N., et al., Principles of Verification: Cycling the Probabilistic Landscape, volume 15262 of LNCS, 2024, Pagina/e 126–154
Editore: Springer
DOI: 10.48550/arxiv.2411.11451

Partially Observable Stochastic Games with Neural Perception Mechanisms

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

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

Autori: Marta Kwiatkowska, Gethin Norman, David Parker, Gabriel Santos
Pubblicato in: Computer Aided Verification - 32nd International Conference, CAV 2020, Los Angeles, CA, USA, July 21–24, 2020, Proceedings, Part II, Numero 12225, 2020, Pagina/e 475-487, ISBN 978-3-030-53290-1
Editore: Springer International Publishing
DOI: 10.1007/978-3-030-53291-8_25

Assessing Robustness of Text Classification through Maximal Safe Radius Computation

Autori: Emanuele La Malfa, Min Wu, Luca Laurenti, Benjie Wang, Anthony Hartshorn, Marta Kwiatkowska
Pubblicato in: Findings of the Association for Computational Linguistics: EMNLP 2020, 2020, Pagina/e 2949-2968
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2020.findings-emnlp.266

Verifying Reinforcement Learning up to Infinity

Autori: Edoardo Bacci, Mirco Giacobbe, David Parker
Pubblicato in: Proceedings, 30th International Joint Conference on Artificial Intelligence (IJCAI-21), 2021
Editore: IJCAI

Multi-agent verification and control with probabilistic model checking

Autori: David Parker
Pubblicato in: Proc. 20th International Conference on Quantitative Evaluation of SysTems (QEST'23), 2023, Pagina/e https://www.qest.org/qest2023/
Editore: Spinger
DOI: 10.48550/arxiv.2308.02829

Learning Dynamics and Generalization in Reinforcement Learning

Autori: Clare Lyle, Mark Rowland, Will Dabney, Marta Kwiatkowska, Yarin Gal
Pubblicato in: Proc. 39th International Conference on Machine Learning (ICML'22), 2022
Editore: PMLR

Correlated equilibria and fairness in concurrent stochastic games

Autori: Marta Kwiatkowska, Gethin Norman, David Parker, Gabriel Santos
Pubblicato in: Tools and Algorithms for the Construction and Analysis of Systems - 28th International Conference, TACAS 2022, 2022, ISSN 0302-9743
Editore: Springer

On Guaranteed Optimal Robust Explanations for NLP Models

Autori: Emanuele La Malfa, Agnieszka Zbrzezny, Rhiannon Michelmore, Nicola Paoletti, Marta Kwiatkowska
Pubblicato in: Proceedings, 30th International Joint Conference on Artificial Intelligence (IJCAI-21), 2021
Editore: IJCAI

Invariant Causal Prediction for Block MDPs

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

Probabilistic Safety for Bayesian Neural Networks

Autori: Matthew Wicker, Luca Laurenti, Andrea Patane, Marta Kwiatkowska
Pubblicato in: Proceedings, 36th Conference on Uncertainty in Artificial Intelligence (UAI 2020), 2020
Editore: PMLR

Strategy Synthesis for Partially Observable Stochastic Games with Neural Perception Mechanisms

Autori: Marta Kwiatkowska
Pubblicato in: 32nd EACSL Annual Conference on Computer Science Logic (CSL 2024), 2024
Editore: Schloss Dagstuhl -- Leibniz-Zentrum fur Informatik
DOI: 10.4230/lipics.csl.2024.5

Tools at the Frontiers of Quantitative Verification

Autori: Roman Andriushchenko et al.
Pubblicato in: TOOLympics III, 2024
Editore: Springer
DOI: 10.48550/arxiv.2405.13583

Adversarial Robustness Guarantees for Classification with Gaussian Processes

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

Probabilistic Timed ATL

Autori: Wojciech Jamroga, Marta Kwiatkowska, Wojciech Penczek, Laure Petrucci, Teofil Sidoruk
Pubblicato in: 24th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2025, 2025
Editore: TBC

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

Autori: Pian Yu, Gianmarco Fedeli and Dimos V. Dimarogonas
Pubblicato in: 9th International Conference on Control, Decision and Information Technologies (CoDIT 2023), 2023
Editore: EEE Xplore
DOI: 10.48550/arxiv.2307.06000

Robustness Guarantees for Deep Neural Networks on Videos

Autori: Min Wu, Marta Kwiatkowska
Pubblicato in: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, Pagina/e 308-317, ISBN 978-1-7281-7168-5
Editore: IEEE
DOI: 10.1109/cvpr42600.2020.00039

Tractable Uncertainty for Structure Learning

Autori: Benjie Wang, Matthew Wicker, Marta Kwiatkowska
Pubblicato in: In 5th Workshop on Tractable Probabilistic Modelling (TPM). This paper was accepted for ICML 2022, Numero 162, 2022, Pagina/e 23131-23150
Editore: PMLR

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

Autori: Yu, Pian; Dong, Shuyang; Sheng, Shili; Feng, Lu; Kwiatkowska, Marta
Pubblicato in: 2024 IEEE International Conference on Robotics and Automation (ICRA2024), 2024
Editore: IEEE
DOI: 10.48550/arxiv.2310.01163

Probabilistic Model Checking: Applications and Trends

Autori: Marta Kwiatkowska, Gethin Norman, David Parker
Pubblicato in: Lecture Notes in Computer Science, Principles of Formal Quantitative Analysis, 2025, Pagina/e 158-173
Editore: Springer Nature Switzerland
DOI: 10.1007/978-3-031-97439-7_7

Symbolic Verification and Strategy Synthesis for Turn-based Stochastic Games

Autori: Marta Kwiatkowska, Gethin Norman, David Parker, Gabriel Santos
Pubblicato in: Principles of Systems Design, Lecture Notes in Computer Science, 2022, Pagina/e 9783031223365, ISBN 978-3-031-22336-5
Editore: Springer
DOI: 10.1007/978-3-031-22337-2_19

Pubblicazioni

Condividi questa pagina Condividi questa pagina sui social network

Scarica Scarica il contenuto della pagina