FUN2MODEL Publications

FUN2MODEL - Publications

Sort by: date, type, title

121 publications:

2026

[Sha26] Daqian Shao. Learning Optimal and Sample-Efficient Decision Policies with Guarantees. Ph.D. thesis, University of Oxford. 2026. [pdf]
[JKP+26] Wojciech Jamroga, Marta Kwiatkowska, Wojciech Penczek, Laure Petrucci and Teofil Sidoruk. Towards Probabilistic Strategic Timed CTL. In Proc. 25th International Conference on Autonomous Agents and Multiagent Systems (AAMAS'26). To appear. 2026. [pdf]
[SBK26] Daqian Shao, Thomas Kleine Buening and Marta Kwiatkowska. Causal Imitation Learning under Expert-Observable and Expert-Unobservable Confounding. In Proc. International Conference on Learning Representation (ICLR'26). To appear. 2026. [pdf]
[LLK26] Minghao Liu, Chia-Hsuan Lu, Marta Kwiatkowska. Exact Verification of Graph Neural Networks with Incremental Constraint Solving. In Proc. 27th International Symposium on Formal Methods (FM'26). 2026. [pdf]
[MRR+26] Anirban Majumdar, Ritam Raha, Rajarshi Roy, David Parker and Marta Kwiatkowska. About Time: Model-free Reinforcement Learning with Timed Reward Machines. In Proc. 35th International Joint Conference on Artificial Intelligence (IJCAI'26). 2026. [pdf]
[SAP26] Yannik Schnitzer, Alessandro Abate and David Parker. Efficient Solution and Learning of Robust Factored MDPs. In Proc. 40th AAAI Conference on Artificial Intelligence (AAAI'26). 2026. [pdf] [bib]

2025

[ZWKZ25] Xiyue Zhang, Benjie Wang, Marta Kwiatkowska, Huan Zhang. PREMAP: A Unifying PREiMage APproximation Framework for Neural Networks. Journal of Machine Learning Research (JMLR). To appear. 2025. [pdf] [bib] https://arxiv.org/abs/2408.09262
[OK25] Pedro Orvalho and Marta Kwiatkowska. Are Large Language Models Robust in Understanding Code Against Semantics-Preserving Mutations?. Technical report , arXiv:2505.10443. Paper under submission. 2025. [pdf] [bib] https://arxiv.org/abs/2505.10443
[OKJM25] Pedro Orvalho, Marta Kwiatkowska, Mikoláš Janota and Vasco Manquinho. Model-Based Diagnosis with Multiple Observations: A Unified Approach for C Software and Boolean Circuits. Technical report arXiv:2512.02898, arxiv. 2025. [pdf] https://arxiv.org/abs/2512.02898
[CSK+25] Terence Daniel Dores Cruz, Christopher Starke, Tim Katzke, Emmanuel Müller, Marta Kwiatkowska, Orly Lobel, Nils Köbis and Shaul Shalvi. Human-in-the-Loop Oversight of AI is Compromised by Political Preferences. Technical report 9ecms_v2, PsyArXiv. 2025. https://osf.io/preprints/psyarxiv/9ecms_v2
[SSQK25] Daqian Shao, Ashkan Soleymani, Francesco Quinzan, Marta Kwiatkowska. Double Machine Learning for Conditional Moment Restrictions: IV regression, Proximal Causal Learning and Beyond. Technical report , arXiv:2506.14950. Paper under submission. 2025. [pdf] [bib] https://arxiv.org/abs/2506.14950
[RPPK25] Rajarshi Roy, Yash Pote, David Parker, Marta Kwiatkowska. Learning Probabilistic Temporal Logic Specifications for Stochastic Systems. In To appear in Proceedings of IJCAI-25. To appear. 2025. [pdf] [bib] https://arxiv.org/abs/2505.12107
[BGMK25] Thomas Kleine Buening, Jiarui Gan, Debmalya Mandal, Marta Kwiatkowska. Strategyproof Reinforcement Learning from Human Feedback. In Proc. 39th Annual Conference on Neural Information Processing Systems (NeurIPS'25). To appear. 2025. [pdf] [bib]
[BNR25] Benjamin Bordais, Daniel Neider, Rajarshi Roy. The Complexity of Learning Temporal Properties. In 42nd International Symposium on Theoretical Aspects of Computer Science (STACS 2025). 2025. [pdf] [bib] https://arxiv.org/abs/2408.04486
[SBK25] Daqian Shao, Thomas Kleine Buening, Marta Kwiatkowska. A Unifying Framework for Causal Imitation Learningwith Hidden Confounders. In Workshop on Spurious Correlation and Shortcut Learning: Foundations and Solutions, Workshop at The International Conference on Learning Representations (ICLR) 2025. 2025. [pdf] [bib] https://arxiv.org/abs/2502.07656
[JKP+25] Wojciech Jamroga, Marta Kwiatkowska, Wojciech Penczek, Laure Petrucci, Teofil Sidoruk. Probabilistic Timed ATL. In Proc. at 24th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2025). 2025. [pdf] [bib]
[OJM25] Pedro Orvalho, Mikolas Janota, Vasco Manquinho. Counterexample Guided Program Repair Using Zero-Shot Learning and MaxSAT-based Fault Localization. In Proc. at Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI-25). To appear. 2025. [pdf] [bib] https://arxiv.org/abs/2502.07786
[YLPK25] Pian Yu, Yong Li, David Parker, Marta Kwiatkowska. Planning with Linear Temporal Logic Specifications: Handling Quantifiable and Unquantifiable Uncertainty. In Proc. at IEEE International Conference on Robotics and Automation (ICRA). To appear. 2025. [pdf] [bib] https://arxiv.org/abs/2502.19603
[OK25b] Pedro Orvalho and Marta Kwiatkowska. PyVeritas: On Verifying Python via LLM-Based Transpilation and Bounded Model Checking for C. In Workshop on Post-AI Formal Methods (AAAI-26, Singapore). Available as arXiv:2508.08171. 2025. [pdf] [bib] https://arxiv.org/abs/2508.08171
[LKF25] Tobias Lorenz, Marta Kwiatkowska and Mario Fritz. MIBP-Cert: Certified Training against Data Perturbations with Mixed-Integer Bilinear Programs. In Proc. 39th Annual Conference on Neural Information Processing Systems (NeurIPS'25). 2025. [pdf] [bib]
[ZWG+25] Xiyue Zhang, Zifan Wang, Yulong Gao, Licio Romao, Alessandro Abate, Marta Kwiatkowska. Risk-Averse Certification of Bayesian Neural Networks. In Proc. SETTA'25. To appear. 2025. [pdf] [bib]
[KNP25] Marta Kwiatkowska, Gethin Norman and David Parker. Probabilistic Model Checking: Applications and Trends. In Principles of Formal Quantitative Analysis: Essays Dedicated to Christel Baier on the Occasion of Her 60th Birthday, volume 15760 of LNCS, pages 158-173, Springer. 2025. [pdf] [bib]
[SAP25] Yannik Schnitzer, Alessandro Abate and David Parker. Certifiably Robust Policies for Uncertain Parametric Environments. In Proc. 31st International Conference on Tools and Algorithms for the Construction and Analysis of Systems (TACAS'25), Springer. 2025. [pdf] [bib]
[BZK25] Anton Björklund, Mykola Zaitsev, Marta Kwiatkowska. Efficient Preimage Approximation for Neural Network Certification. Technical report 2505.22798, arxiv. Paper under submission. 2025. [pdf] [bib] https://arxiv.org/abs/2505.22798
[BCC+25] Tomáš Brázdil, Krishnendu Chatterjee, Martin Chmelik, Vojtěch Forejt, Jan Křetínský, Marta Kwiatkowska, Tobias Meggendorfer, David Parker, Mateusz Ujma. Learning Algorithms for Verification of Markov Decision Processes. TheoretiCS, 4. April 2025. [pdf] [bib] https://arxiv.org/abs/2403.09184

2024

[VSLK24] Jon Vadillo, Roberto Santana, Jose A. Lozano, Marta Kwiatkowska. Uncertainty-Aware Explanations Through Probabilistic Self-Explainable Neural Networks. Technical report , arXiv:2403.13740 . Paper under submission. 2024. [pdf] [bib] https://arxiv.org/abs/2403.13740
[SFK24] Daqian Shao, Lukas Fesser, Marta Kwiatkowska. STR-Cert: Robustness Certification for Deep Text Recognition on Deep Learning Pipelines and Vision Transformers. Technical report , arXiv:2401.05338. Paper under submission. 2024. [pdf] [bib] https://arxiv.org/abs/2401.05338
[YSN+24b] Rui Yan, Gabriel Santos, Gethin Norman, David Parker, Marta Kwiatkowska. Partially Observable Stochastic Games with Neural Perception Mechanisms. In Proc. 26th International Symposium on Formal Methods (FM'24), Springer. To appear. 2024. [pdf] [bib]
[YZD+24] Pian Yu, Shufang Zhu, Giuseppe De Giacomo, Marta Kwiatkowska and Moshe Vardi. The Trembling-Hand Problem for LTLf Planning. In Proc. 33rd International Joint Conference on Artificial Intelligence (IJCAI'24). 2024. [pdf] [bib] https://doi.org/10.48550/arXiv.2404.16163
[YDS+24] Pian Yu, Shuyang Dong, Shili Sheng, Lu Feng, Marta Kwiatkowska. Trust-Aware Motion Planning for Human-Robot Collaboration under Distribution Temporal Logic Specifications. In Proc. IEEE International Conference on Robotics and Automation (ICRA'24). 2024. [pdf] [bib] https://arxiv.org/abs/2310.01163
[ZWK24] Xiyue Zhang, Benjie Wang, Marta Kwiatkowska. Provable preimage under-approximation for neural networks. In Proc. 30th International Conference on Tools and Algorithms for the Construction and Analysis of Systems (TACAS 2024), Springer. 2024. [pdf] [bib]
[EPF24] Ingy Elsayed-Aly, David Parker and Lu Feng. Distributional Probabilistic Model Checking. In Proc. 16th NASA Formal Methods Symposium (NFM'24), volume 14627 of LNCS, pages 57-75, Springer. 2024. [pdf] [bib]
[ABB+24] 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 and Zhen Zhang. Tools at the Frontiers of Quantitative Verification. In Proc. TOOLympics III, volume 14550 of LNCS, pages 90-146, Springer. 2024. [pdf] [bib]
[SPF24] Shili Sheng, David Parker and Lu Feng. Safe POMDP Online Planning via Shielding. In Proc. IEEE International Conference on Robotics and Automation (ICRA'24). 2024. [pdf] [bib]
[Kwi24] Marta Kwiatkowska. Strategy Synthesis for Partially Observable Stochastic Games with Neural Perception Mechanisms. In 32nd EACSL Annual Conference on Computer Science Logic (CSL 2024). 2024. [pdf] [bib] https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.CSL.2024.5
[WPL+24] Matthew Wicker, Andrea Patane, Luca Laurenti, Marta Kwiatkowska. Adversarial Robustness Certification for Bayesian Neural Networks. In Proc. 26th International Symposium on Formal Methods (FM'24 invited paper), Springer. To appear. 2024. [pdf] [bib] https://arxiv.org/abs/2306.13614
[NR24] Daniel Neider and Rajarshi Roy. What Is Formal Verification Without Specifications? A Survey on Mining LTL Specifications. In Jansen, N., et al. Principles of Verification: Cycling the Probabilistic Landscape. Lecture Notes in Computer Science, Springer. 2024. [pdf] [bib]
[SBB+24] Marnix Suilen, Thom Badings, Eline M. Bovy, David Parker and Nils Jansen. Robust Markov Decision Processes: A Place Where AI and Formal Methods Meet. In Principles of Verification: Cycling the Probabilistic Landscape,, pages 126–154, Springer. 2024. [pdf] [bib]
[KNPS24] Marta Kwiatkowska, Gethin Norman, David Parker and Gabriel Santos. Expectation vs. Reality: Towards Verification of Psychological Games. In Principles of Verification: Cycling the Probabilistic Landscape, pages 166–191, Springer. 2024. [pdf] [bib]
[CWZS24] Jialuo Chen, Jingyi Wang, Xiyue Zhang, Youcheng Sun, Marta Kwiatkowska, Jiming Chen, Peng Cheng. FAST: Boosting Uncertainty-based Test Prioritization Methods for Neural Networks via Feature Selection. In 39th IEEE/ACM International Conference on Automated Software Engineering (ASE 2024). To appear. 2024. [pdf] [bib] https://arxiv.org/abs/2409.09130
[LKF24] Tobias Lorenz, Marta Kwiatkowska, Mario Fritz . FullCert: Deterministic End-to-End Certification for Training and Inference of Neural Networks. In The German Conference on Pattern Recognition (GCPR), Springer Nature. To appear. 2024. [pdf] [bib]
[YSN+24] Rui Yan, Gabriel Santos, Gethin Norman, David Parker and Marta Kwiatkowska. HSVI-based Online Minimax Strategies for Partially Observable Stochastic Games with Neural Perception Mechanisms. In Proc. Learning for Dynamics and Control Conference (L4DC'24), volume 242 of Proceedings of Machine Learning Research, pages 80-91. 2024. [pdf] [bib]
[KZH+24] Matthias König, Xiyue Zhang, Holger H. Hoos, Marta Kwiatkowska, Jan N. van Rijn. Automated Design of Linear Bounding Functions for Sigmoidal Nonlinearities in Neural Networks. In Proc. at (ECML-PKDD 2024) European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases. 2024. [pdf] [bib] https://arxiv.org/abs/2406.10154
[SSQK24] Daqian Shao, Ashkan Soleymani, Francesco Quinzan, Marta Kwiatkowska. Learning Decision Policies with Instrumental Variables through Double Machine Learning. In Proc. 41st International Conference on Machine Learning (ICML 2024). 2024. [pdf] [bib] https://arxiv.org/abs/2405.08498
[WLP+24] Matthew Wicker, Luca Laurenti, Andrea Patane, Nicola Paoletti, Alessandro Abate, Marta Kwiatkowska.. Probabilistic Reach-Avoid for Bayesian Neural Networks. Artificial Intelligence. To appear in Artificial Intelligence. 2024. [pdf] [bib] https://arxiv.org/abs/2310.01951
[SYP+24] Shili Sheng, Pian Yu, David Parker, Marta Kwiatkowska, Lu Feng. Safe POMDP Online Planning among Dynamic Agents via Adaptive Conformal Prediction. IEEE Robotics and Automation Letters (RA-L), 11(9), pages 9946-9953. 2024. [pdf] [bib]
[YSN+24c] Rui Yan, Gabriel Santos, Gethin Norman, David Parker and Marta Kwiatkowska. Strategy Synthesis for Zero-sum Neuro-symbolic Concurrent Stochastic Games. Information and Computation. To appear. 2024. [pdf] [bib]
[FLHP24] Fatma Faruq, Bruno Lacerda, Nick Hawes and David Parker. A Framework for Simultaneous Task Allocation and Planning under Uncertainty. ACM Transactions on Autonomous and Adaptive Systems. 2024. [pdf] [bib]
[YDZ+24] Rui Yan, Xiaoming Duan, Rui Zou, Xin He, Zongying Shi, Francesco Bullo. Multiplayer Homicidal Chauffeur Reach-Avoid Games: A Pursuit Enclosure Function Approach. Automatica. Paper accepted April 2024. 2024. [pdf] [bib] https://arxiv.org/abs/2311.02389

2023

[YGJ+23] Pian Yu, Yulong Gao, Frank J. Jiang, Karl H. Johansson and Dimos V. Dimarogonas. Online control synthesis for uncertain systems under signal temporal logic specifications. International Journal of Robotics Research, SAGE Publications. 2023. [pdf] [bib]
[WK23] Benjie Wang and Marta Kwiatkowska. Compositional Probabilistic and Causal Inference using Tractable Circuit Models. In Proc. 26th International Conference on Artificial Intelligence and Statistics (AISTATS). 2023. [pdf] [bib]
[SK23] Daqian Shao, Marta Kwiatkowska. Sample Efficient Model-free Reinforcement Learning from LTL Specifications with Optimality Guarantees. In Proc. 32nd International Joint Conference on Artificial Intelligence (IJCAI'23). 2023. [pdf] [bib]
[QSJ+23] Francesco Quinzan, Ashkan Soleymani, Patrik Jaillet, Cristian R. Rojas, Stefan Bauer. DRCFS: Doubly Robust Causal Feature Selection. In ICML2023 Fortieth International Conference on Machine Learning. To appear. 2023. [pdf] [bib]
[Kwi23] Marta Kwiatkowska. Robust Decision Pipelines: Opportunities and Challenges for AI in Business Process Modelling. In BPM 2023 Forum, Utrecht, The Netherlands, A Springer Nature Computer Science book series. To appear. 2023. [pdf] [bib]
[YSN+23] Rui Yan, Gabriel Santos, Gethin Norman, David Parker, Marta Kwiatkowska. Point-based Value Iteration for Neuro-Symbolic POMDPs. Technical report arXiv:2306.17639, arXiv. Paper under submission. 2023. [pdf] [bib] https://arxiv.org/abs/2306.17639
[YFD23] Pian Yu, Gianmarco Fedeli, Dimos V. Dimarogonas. Reactive and human-in-the-loop planning and control of multi-robot systems under LTL specifications in dynamic environments. In 9th International Conference on Control, Decision and Information Technologies (CoDIT 2023). 2023. [pdf] [bib]
[Wan23] Benjie Wang. Tractable probabilistic models for causal learning and reasoning. Ph.D. thesis, Department of Computer Science, University of Oxford. 2023. [pdf] [bib]
[Par23] David Parker. Multi-Agent Verification and Control with Probabilistic Model Checking. In Proc. 20th International Conference on Quantitative Evaluation of SysTems (QEST'23), Springer. 2023. [pdf] [bib]
[WZZS23] Zeming Wei, Xiyue Zhang, Yihao Zhang, Meng Sun. Weighted Automata Extraction and Explanation of Recurrent Neural Networks for Natural Language Tasks. Journal of Logical and Algebraic Methods in Programming, Elsevier. 2023. [pdf] [bib]
[KZ23] Marta Kwiatkowska, Xiyue Zhang. When to Trust AI: Advances and Challenges for Certification of Neural Networks. In Proceedings of the 18th Conference on Computer Science and Intelligence Systems (FedCSIS 2023). To appear. 2023. [pdf] [bib]
[Gou23] Pascale Gourdeau. Sample complexity of robust learning against evasion attacks. Ph.D. thesis, Department of Computer Science, University of Oxford. 2023. [pdf] [bib]
[LKF23] Tobias Lorenz, Marta Kwiatkowska and Mario Fritz. Certifiers Make Neural Networks Vulnerable to Availability Attacks. In 16th ACM Workshop on Artificial Intelligence and Security (AISec 2023). To appear. 2023. [pdf] [bib]
[YZD+23] Rui Yan, Weixian Zhang, Ruiliang Deng, Xiaoming Duan, Zongying Shi, Yisheng Zhong. Evaluation and learning in two-player symmetric games via best and better response. Information Sciences, 647, pages 119459, Elsevier. 2023. [pdf] [bib] https://doi.org/10.1016/j.ins.2023.119459
[LWK23] Emanuele La Malfa, Matthew Wicker, Marta Kwiatkowska. Emergent Linguistic Structures in Neural Networks are Fragile. Technical report , arXiv. 2023. [pdf] [bib] https://arxiv.org/abs/2210.17406
[Lam23] Emanuele La Malfa. On Robustness for Natural Language Processing. Ph.D. thesis, Department of Computer Science, University of Oxford. 2023. [pdf] [bib]
[BRA+23] Thom Badings, Licio Romao, Alessandro Abate, David Parker, Hasan A. Poonawala, Marielle Stoelinga and Nils Jansen. Robust Control for Dynamical Systems with Non-Gaussian Noise via Formal Abstractions. Journal of Artificial Intelligence Research, 76, pages 341-391. January 2023. [pdf] [bib]

2022

[VWM22] Artem Velikzhanin, Benjie Wang and Marta Kwiatkowska. Bayesian Network Models of Causal Interventions in Healthcare Decision Making: Literature Review and Software Evaluation. Technical report , Computer Science, University of Oxford. 2022. [pdf] [bib] https://arxiv.org/abs/2211.15258
[KNPS22b] Marta Kwiatkowska, Gethin Norman, David Parker and Gabriel Santos. Symbolic Verification and Strategy Synthesis for Turn-based Stochastic Games. In Principles of Systems Design: Essays Dedicated to Thomas A. Henzinger on the Occasion of His 60th Birthday, volume 13660 of LNCS, Springer. 2022. [pdf] [bib]
[Wic22] Matthew Wicker. Adversarial Robustness of Bayesian Neural Networks. Ph.D. thesis, Department of Computer Science, University of Oxford. 2022. [pdf] [bib]
[PBL+22] Andrea Patane, Arno Blaas, Luca Laurenti, Luca Cardelli, Stephen Roberts and Marta Kwiatkowska. Adversarial Robustness Guarantees for Gaussian Processes. Journal of Machine Learning Research, 23, pages 1-55. 2022. [pdf] [bib]
[PK22] Aleksandar Petrov, Marta Kwiatkowska. Robustness of Unsupervised Representation Learning without Labels. Technical report arXiv:2210.04076, arXiv. 2022. [pdf] [bib] https://doi.org/10.48550/arXiv.2210.04076
[Ole22] Maciej Olejnik. Modelling Human-Like Decision Making and Social Trust Using Probabilistic Programming. Ph.D. thesis, Department of Computer Science, University of Oxford. 2022. [pdf] [bib]
[Kwi22] Marta Kwiatkowska. Robustness Guarantees for Bayesian Neural Networks. In Proc. 19th International Conference on Quantitative Evaluation of SysTems (QEST 2022). 2022. [pdf] [bib]
[WWK22c] Benjie Wang and Matthew Wicker and Marta Kwiatkowska. Tractable Uncertainty for Structure Learning. In 5th Workshop on Tractable Probabilistic Modelling (TPM). This paper was accepted for ICML 2022. 2022. [pdf] [bib]
[SPH+22] Shili Sheng, Erfan Pakdamanian, Kyungtae Han, Ziran Wang, John Lenneman, David Parker and Lu Feng. Planning for Automated Vehicles with Human Trust. Association for Computing Machinery (ACM) Transactions on Cyber-Physical Systems. To appear September. 2022. [pdf] [bib]
[Fal22] Rhiannon Falconmore. On the Role of Explainability and Uncertainty in Ensuring Safety of AI Applications. Ph.D. thesis, Department of Computer Science, University of Oxford. 2022. [pdf] [bib]
[GPL+22] Shadi Ghiasi, Andrea Patane, Luca Laurenti, Claudio Gentili, Enzo Pasquale Scilingo, Alberto Greco and Marta Kwiatkowska. Physiologically-Informed Gaussian Processes for Interpretable Modelling of Psycho-Physiological States. EEE Journal of Biomedical and Health Informatics (J-BHI). 2022. [pdf] [bib]
[WK22] Benjie Wang and Marta Kwiatkowska. Symbolic Causal Inference via Operations on Probabilistic Circuits. In NeurIPS Workshop on Neuro Causal and Symbolic AI (nCSI'22). 2022. [pdf] [bib]
[SSJP22] Marnix Suilen, Thiago D. Simão, Nils Jansen and David Parker. Robust Anytime Learning of Markov Decision Processes. In Proc. 36th Annual Conference on Neural Information Processing Systems (NeurIPS'22). November 2022. [pdf] [bib]
[KNP+22] Marta Kwiatkowska, Gethin Norman, David Parker, Gabriel Santos and Rui Yan. Probabilistic Model Checking for Strategic Equilibria-based Decision Making: Advances and Challenges. In Proc. 47th International Symposium on Mathematical Foundations of Computer Science (MFCS'22). August 2022. [pdf] [bib]
[YSD+22] Rui Yan, Gabriel Santos, Xiaoming Duan, David Parker and Marta Kwiatkowska. Finite-horizon Equilibria for Neuro-symbolic Concurrent Stochastic Games. In Proc. 38th Conference on Uncertainty in Artificial Intelligence (UAI'22), AUAI Press. August 2022. [pdf] [bib]
[WWK22b] Benjie Wang, Matthew Wicker and Marta Kwiatkowska. Tractable Uncertainty for Structure Learning. In Proc. 39th International Conference on Machine Learning (ICML'22). To appear. July 2022. [pdf] [bib]
[BPW+22] Elias Benussi, Andrea Patane, Matthew Wicker, Luca Laurenti and Marta Kwiatkowska. Individual Fairness Guarantees for Neural Networks. In Proc. 31st International Joint Conference on Artificial Intelligence (IJCAI'22). To appear. July 2022. [pdf] [bib]
[GKKW22] Pascale Gourdeau, Varun Kanade, Marta Kwiatkowska and James Worrell. Sample Complexity Bounds for Robustly Learning Decision Lists against Evasion Attacks. In Proc. 31st International Joint Conference on Artificial Intelligence (IJCAI'22). To appear. July 2022. [pdf] [bib]
[LRD+22] Clare Lyle, Mark Rowland, Will Dabney, Marta Kwiatkowska and Yarin Gal. Learning Dynamics and Generalization in Reinforcement Learning. In Proc. 39th International Conference on Machine Learning (ICML'22). To appear. July 2022. [pdf] [bib]
[WWK22] Hjalmar Wijk, Benjie Wang and Marta Kwiatkowska. Robustness Guarantees for Credal Bayesian Networks via Constraint Relaxation over Probabilistic Circuits. In Proc. 31st International Joint Conference on Artificial Intelligence (IJCAI'22). To appear. July 2022. [pdf] [bib]
[CBPF22] Shenghui Chen, Kayla Boggess, David Parker and Lu Feng. Multi-Objective Controller Synthesis with Uncertain Human Preferences. In Proc. ACM/IEEE 13th International Conference on Cyber-Physical Systems (ICCPS'22), ACM. May 2022. [pdf] [bib]
[KNP22] Marta Kwiatkowska, Gethin Norman and David Parker. Probabilistic Model Checking and Autonomy. Annual Review of Control, Robotics, and Autonomous Systems, 5, Annual Reviews, 5, pages 385-410. May 2022. [pdf] [bib]
[BP22] Edoardo Bacci and David Parker. Verified Probabilistic Policies for Deep Reinforcement Learning. In Proc. 14th International Symposium NASA Formal Methods (NFM'22), volume 13260 of LNCS, pages 193-212, Springer. May 2022. [pdf] [bib]
[KNPS22] Marta Kwiatkowska, Gethin Norman, David Parker and Gabriel Santos. Correlated Equilibria and Fairness in Concurrent Stochastic Games. In Proc. 28th International Conference on Tools and Algorithms for the Construction and Analysis of Systems (TACAS'22), volume 13244 of LNCS, pages 60–78, Springer. April 2022. [pdf] [bib]
[LK22] Emanuele La Malfa and Marta Kwiatkowska. The King is Naked: on the Notion of Robustness for Natural Language Processing. In Proc. 36th AAAI Conference on Artificial Intelligence (AAAI'22). To appear. March 2022. [pdf] [bib]
[Bac22] Edoardo Bacci. Formal Verification of Deep Reinforcement Learning Agents. Ph.D. thesis, School of Computer Science, University of Birmingham. March 2022. [pdf] [bib]
[BAJ+22] Thom S. Badings, Alessandro Abate, Nils Jansen, David Parker, Hasan A. Poonawala and Marielle Stoelinga. Sampling-Based Robust Control of Autonomous Systems with Non-Gaussian Noise. In Proc. 36th AAAI Conference on Artificial Intelligence (AAAI'22). March 2022. [pdf] [bib]
[GKKW22b] Pascale Gourdeau, Varun Kanade, Marta Kwiatkowska, James Worrell. When are Local Queries Useful for Robust Learning?. In Proc. 36th Conference on Neural Information Processing Systems (NeurIPS'22). 2022. [pdf] [bib]

2021

[KJI+21] Hannah Rose Kirk, Yennie Jun, Haider Iqbal, Elias Benussi, Filippo Volpin, Frederic A. Dreyer, Aleksandar Shtedritski, Yuki M. Asano. Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models. In Conference on Neural Information Processing Systems (NeurIPS'21). To appear. December 2021. [pdf] [bib]
[GKK+21] Pascale Gourdeau, Varun Kanade, Marta Kwiatkowska and James Worrell. On the Hardness of Robust Classification. Journal of Machine Learning Research (JMLR), 22(273), pages 1-29. October 2021. [pdf] [bib]
[CKL21] Luca Cardelli, Marta Kwiatkowska and Luca Laurenti. A Language for Modeling And Optimizing Experimental Biological Protocols. Computation, MDPI. October 2021. [pdf] [bib]
[LZM+21] Emanuele La Malfa, Agnieszka Zbrzezny, Rhiannon Michelmore, Nicola Paoletti and Marta Kwiatkowska. On Guaranteed Optimal Robust Explanations for NLP Models. In 30th International Joint Conference on Artificial Intelligence (IJCAI'21). August 2021. [pdf] [bib]
[LKF21] Tobias Lorenz, Marta Kwiatkowska and Mario Fritz. Uncertify: Attacks Against Neural Network Certification. Technical report , Arxiv:2108.11299. Superseded by [LKF23] http://fun2model.org/bibitem.php?key=LKF23. August 2021. [pdf] [bib]
[BGP21] Edoardo Bacci, Mirco Giacobbe and David Parker. Verifying Reinforcement Learning up to Infinity. In 30th International Joint Conference on Artificial Intelligence (IJCAI'21). August 2021. [pdf] [bib]
[AGH+21] Alessandro Abate, Julian Gutierrez, Lewis Hammond, Paul Harrenstein, Marta Kwiatkowska, Muhammad Najib, Giuseppe Perelli, Thomas Steeples and Michael Wooldridge. Rational verification: game-theoretic verification of multi-agent systems. Applied Intelligence, Springer. August 2021. [pdf] [bib]
[WLK21] Benjie Wang, Clare Lyle and Marta Kwiatkowska. Provable Guarantees on the Robustness of Decision Rules to Causal Interventions. In 30th International Joint Conference on Artificial Intelligence (IJCAI'21). August 2021. [pdf] [bib]
[WLP+21a] Matthew Wicker, Luca Laurenti, Andrea Patane, Nicola Paoletti, Alessandro Abate and Marta Kwiatkowska. Certification of Iterative Predictions in Bayesian Neural Networks. In 37th Conference on Uncertainty in Artificial Intelligence (UAI'21). May 2021. [pdf] [bib]
[WLP+21] Matthew Wicker, Luca Laurenti, Andrea Patane, Zhuotong Chen, Zheng Zhang and Marta Kwiatkowska. Bayesian Inference with Certifiable Adversarial Robustness. In International Conference on Artificial Intelligence and Statistics (AISTATS'21), PMLR. April 2021. [pdf] [bib]
[San21] Gabriel H.R. Santos. Automatic Verification and Strategy Synthesis for Zero-sum and Equilibria Properties of Concurrent Stochastic Games. Ph.D. thesis, Department of Computer Science, University of Oxford. March 2021. [pdf] [bib]
[Pat21] Andrea Patane. On the Adversarial Robustness of Gaussian Processes. Ph.D. thesis, Department of Computer Science, University of Oxford. February 2021. [pdf] [bib]
[KNPS21] Marta Kwiatkowska, Gethin Norman, David Parker and Gabriel Santos. Automated Verification of Concurrent Stochastic Systems. Formal Methods in System Design, Springer. January 2021. [pdf] [bib]

2020

[PLP+20] Kyriakos Polymenakos, Luca Laurenti, Andrea Patane, Jan-Peter Calliess, Luca Cardelli, Marta Kwiatkowska, Alessandro Abate and Stephen Roberts. Safety Guarantees for Iterative Predictions with Gaussian Processes. In 59th Conference on Decision and Control (CDC'20), IEEE. December 2020. [pdf] [bib]
[LWL+20] Emanuele La Malfa, Min Wu, Luca Laurenti, Benjie Wang, Anthony Hartshorn and Marta Kwiatkowska. Assessing Robustness of Text Classification through Maximal Safe Radius Computation. In Conference on Empirical Methods in Natural Language Processing (EMNLP'20), ACL. November 2020. [pdf] [bib]
[BHK+20] Carlos E. Budde, Arnd Hartmanns, Michaela Klauck, Jan Kretínský, David Parker, Tim Quatmann, Andrea Turrini, and Zhen Zhang. On Correctness, Precision, and Performance in Quantitative Verification: QComp 2020 Competition Report. In 9th International Symposium on Leveraging Applications of Formal Methods, Verification and Validation (ISoLA'20), Springer. October 2020. [pdf] [bib]
[Kwi20] Marta Kwiatkowska. Safety and Robustness for Deep Learning with Provable Guarantees. In 35th IEEE/ACM International Conference on Automated Software Engineering, (ASE’20), ACM. September 2020. [pdf] [bib]
[BP20] Edoardo Bacci and David Parker. Probabilistic Guarantees for Safe Deep Reinforcement Learning. In 18th International Conference on Formal Modelling and Analysis of Timed Systems (FORMATS'20), Springer. September 2020. [pdf] [bib]
[WLPK20] Matthew Wicker, Luca Laurenti, Andrea Patane and Marta Kwiatkowska. Probabilistic Safety for Bayesian Neural Networks. In 36th Conference on Uncertainty in Artificial Intelligence (UAI'20), PMLR. August 2020. [pdf] [bib]
[KNPS20b] Marta Kwiatkowska, Gethin Norman, David Parker, and Gabriel Santos. Multi-player Equilibria Verification for Concurrent Stochastic Games. In 17th International Conference on Quantitative Evaluation of SysTems (QEST'20), Springer. August 2020. [pdf] [bib]
[BPL+20] Arno Blaas, Andrea Patane, Luca Laurenti, Luca Cardelli, Marta Kwiatkowska and Stephen Roberts. Adversarial Robustness Guarantees for Classification with Gaussian Processes. In 23rd International Conference on Artificial Intelligence and Statistics (AISTATS'20), PMLR. August 2020. [pdf] [bib]
[KNPS20] Marta Kwiatkowska, Gethin Norman, David Parker and Gabriel Santos. PRISM-games 3.0: Stochastic Game Verification with Concurrency, Equilibria and Time. In 32nd International Conference on Computer Aided Verification (CAV'20), Springer. July 2020. [pdf] [bib]
[ZLS+20] Amy Zhang, Clare Lyle, Shagun Sodhani, Angelos Filos, Marta Kwiatkowska, Joelle Pineau, Yarin Gal, Doina Precup. Invariant Causal Prediction for Block MDPs. In International Conference on Machine Learning (ICML'20), PMLR. July 2020. [pdf] [bib]
[WK20] Min Wu and Marta Kwiatkowska. Robustness Guarantees for Deep Neural Networks on Videos. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR'20), IEEE. June 2020. [pdf] [bib]
[Wu20] Min Wu. Robustness Evaluation of Deep Neural Networks with Provable Guarantees. Ph.D. thesis, Department of Computer Science, University of Oxford. May 2020. [pdf] [bib]
[LVK+20] Clare Lyle, Mark van der Wilk, Marta Kwiatkowska, Yarin Gal and Benjamin Bloem-Reddy. On the Benefits of Invariance in Neural Networks. Technical report , arXiv. Presented as poster at the NeurIPS 2019 Machine Learning with Guarantees Workshop. May 2020. [pdf] [bib]

2019

[Kwi19] Marta Kwiatkowska. Safety Verification for Deep Neural Networks with Provable Guarantees (Invited Paper). In 30th International Conference on Concurrency Theory (CONCUR'19), Dagstuhl Publishing. August 2019. [pdf] [bib]

Sort by: date, type, title