[{"month":"06","OA_place":"publisher","status":"public","project":[{"name":"Vigilant Algorithmic Monitoring of Software","call_identifier":"H2020","grant_number":"101020093","_id":"62781420-2b32-11ec-9570-8d9b63373d4d"}],"author":[{"orcid":"0000-0002-2985-7724","full_name":"Henzinger, Thomas A","id":"40876CD8-F248-11E8-B48F-1D18A9856A87","first_name":"Thomas A","last_name":"Henzinger"},{"id":"faff3c84-23f6-11ef-9085-e5187b51c604","full_name":"Kresse, Fabian","first_name":"Fabian","last_name":"Kresse"},{"last_name":"Mallik","id":"0834ff3c-6d72-11ec-94e0-b5b0a4fb8598","full_name":"Mallik, Kaushik","first_name":"Kaushik","orcid":"0000-0001-9864-7475"},{"last_name":"Yu","full_name":"Yu, Zhengqi","id":"20aa2ae8-f2f1-11ed-bbfa-8205053f1342","first_name":"Zhengqi"},{"orcid":"0000-0002-4681-1699","last_name":"Zikelic","id":"294AA7A6-F248-11E8-B48F-1D18A9856A87","full_name":"Zikelic, Dorde","first_name":"Dorde"}],"quality_controlled":"1","publication_status":"published","file_date_updated":"2025-09-03T10:32:12Z","_id":"20256","page":"804-816","file":[{"file_size":489639,"success":1,"date_updated":"2025-09-03T10:32:12Z","file_id":"20283","file_name":"2025_L4DC_HenzingerT.pdf","date_created":"2025-09-03T10:32:12Z","relation":"main_file","content_type":"application/pdf","access_level":"open_access","creator":"dernst","checksum":"d5236e561560635f5ae1d17de4903033"}],"year":"2025","title":"Predictive monitoring of black-box dynamical systems","corr_author":"1","publisher":"ML Research Press","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","department":[{"_id":"ToHe"},{"_id":"ChLa"}],"ddc":["000"],"language":[{"iso":"eng"}],"volume":283,"date_published":"2025-06-01T00:00:00Z","alternative_title":["PMLR"],"publication":"7th Annual Learning for Dynamics & Control Conference","OA_type":"gold","external_id":{"arxiv":["2412.16564"]},"has_accepted_license":"1","intvolume":"       283","ec_funded":1,"day":"01","acknowledgement":"This work was supported in part by the ERC project ERC-2020-AdG 101020093.\r\n","conference":{"name":"L4DC: Learning for Dynamics & Control","end_date":"2025-06-06","start_date":"2025-06-04","location":"Ann Arbor, MI, United States"},"article_processing_charge":"No","date_created":"2025-08-31T22:01:32Z","abstract":[{"lang":"eng","text":"We study the problem of predictive runtime monitoring of black-box dynamical systems with quantitative safety properties. The black-box setting stipulates that the exact semantics of the dynamical system and the controller are unknown, and that we are only able to observe the state of the controlled (aka, closed-loop) system at finitely many time points. We present a novel framework for predicting future states of the system based on the states observed in the past. The numbers of past states and of predicted future states are parameters provided by the user. Our method is based on a combination of Taylor’s expansion and the backward difference operator for numerical differentiation. We also derive an upper bound on the prediction error under the assumption that the system dynamics and the controller are smooth. The predicted states are then used to predict safety violations ahead in time. Our experiments demonstrate practical applicability of our method for complex black-box systems, showing that it is computationally lightweight and yet significantly more accurate than the state-of-the-art predictive safety monitoring techniques."}],"type":"conference","citation":{"chicago":"Henzinger, Thomas A, Fabian Kresse, Kaushik Mallik, Emily Yu, and Dorde Zikelic. “Predictive Monitoring of Black-Box Dynamical Systems.” In <i>7th Annual Learning for Dynamics &#38; Control Conference</i>, 283:804–16. ML Research Press, 2025.","apa":"Henzinger, T. A., Kresse, F., Mallik, K., Yu, E., &#38; Zikelic, D. (2025). Predictive monitoring of black-box dynamical systems. In <i>7th Annual Learning for Dynamics &#38; Control Conference</i> (Vol. 283, pp. 804–816). Ann Arbor, MI, United States: ML Research Press.","mla":"Henzinger, Thomas A., et al. “Predictive Monitoring of Black-Box Dynamical Systems.” <i>7th Annual Learning for Dynamics &#38; Control Conference</i>, vol. 283, ML Research Press, 2025, pp. 804–16.","ieee":"T. A. Henzinger, F. Kresse, K. Mallik, E. Yu, and D. Zikelic, “Predictive monitoring of black-box dynamical systems,” in <i>7th Annual Learning for Dynamics &#38; Control Conference</i>, Ann Arbor, MI, United States, 2025, vol. 283, pp. 804–816.","ista":"Henzinger TA, Kresse F, Mallik K, Yu E, Zikelic D. 2025. Predictive monitoring of black-box dynamical systems. 7th Annual Learning for Dynamics &#38; Control Conference. L4DC: Learning for Dynamics &#38; Control, PMLR, vol. 283, 804–816.","short":"T.A. Henzinger, F. Kresse, K. Mallik, E. Yu, D. Zikelic, in:, 7th Annual Learning for Dynamics &#38; Control Conference, ML Research Press, 2025, pp. 804–816.","ama":"Henzinger TA, Kresse F, Mallik K, Yu E, Zikelic D. Predictive monitoring of black-box dynamical systems. In: <i>7th Annual Learning for Dynamics &#38; Control Conference</i>. Vol 283. ML Research Press; 2025:804-816."},"oa":1,"arxiv":1,"date_updated":"2025-09-03T10:37:59Z","oa_version":"Published Version","scopus_import":"1","publication_identifier":{"eissn":["2640-3498"]}},{"oa_version":"Published Version","scopus_import":"1","publication_identifier":{"eissn":["2640-3498"]},"conference":{"name":"NeuS: International Conferenceon Neuro-Symbolic Systems","end_date":"2025-05-30","location":"Philadephia, PA, United States","start_date":"2025-05-28"},"acknowledgement":"This work is supported in part by the ERC grant under Grant No. ERC-2020-AdG 101020093 and\r\nthe Austrian Science Fund (FWF) [10.55776/COE12]. This research was supported by the Scientific\r\nService Units (SSU) of ISTA through resources provided by Scientific Computing (SciComp).","article_number":"26","article_processing_charge":"No","type":"conference","abstract":[{"lang":"eng","text":"Learning-based systems are increasingly deployed across various domains, yet the complexity of traditional neural networks poses significant challenges for formal verification. Unlike conventional neural networks, learned Logic Gate Networks (LGNs) replace multiplications with Boolean logic gates, yielding a sparse, netlist-like architecture that is inherently more amenable to symbolic verification, while still delivering promising performance. In this paper, we introduce a SAT encoding for verifying global robustness and fairness in LGNs. We evaluate our method on five benchmark datasets, including a newly constructed 5-class variant, and find that LGNs are both verification-friendly and maintain strong predictive performance."}],"date_created":"2025-09-07T22:01:34Z","date_updated":"2025-09-09T08:12:44Z","citation":{"ista":"Kresse F, Yu E, Lampert C, Henzinger TA. 2025. Logic gate neural networks are good for verification. 2nd International Conferenceon Neuro-Symbolic Systems. NeuS: International Conferenceon Neuro-Symbolic Systems, PMLR, vol. 288, 26.","short":"F. Kresse, E. Yu, C. Lampert, T.A. Henzinger, in:, 2nd International Conferenceon Neuro-Symbolic Systems, ML Research Press, 2025.","ama":"Kresse F, Yu E, Lampert C, Henzinger TA. Logic gate neural networks are good for verification. In: <i>2nd International Conferenceon Neuro-Symbolic Systems</i>. Vol 288. ML Research Press; 2025.","chicago":"Kresse, Fabian, Emily Yu, Christoph Lampert, and Thomas A Henzinger. “Logic Gate Neural Networks Are Good for Verification.” In <i>2nd International Conferenceon Neuro-Symbolic Systems</i>, Vol. 288. ML Research Press, 2025.","apa":"Kresse, F., Yu, E., Lampert, C., &#38; Henzinger, T. A. (2025). Logic gate neural networks are good for verification. In <i>2nd International Conferenceon Neuro-Symbolic Systems</i> (Vol. 288). Philadephia, PA, United States: ML Research Press.","ieee":"F. Kresse, E. Yu, C. Lampert, and T. A. Henzinger, “Logic gate neural networks are good for verification,” in <i>2nd International Conferenceon Neuro-Symbolic Systems</i>, Philadephia, PA, United States, 2025, vol. 288.","mla":"Kresse, Fabian, et al. “Logic Gate Neural Networks Are Good for Verification.” <i>2nd International Conferenceon Neuro-Symbolic Systems</i>, vol. 288, 26, ML Research Press, 2025."},"arxiv":1,"oa":1,"alternative_title":["PMLR"],"publication":"2nd International Conferenceon Neuro-Symbolic Systems","OA_type":"diamond","has_accepted_license":"1","external_id":{"arxiv":["2505.19932"]},"day":"01","intvolume":"       288","ec_funded":1,"department":[{"_id":"ChLa"},{"_id":"ToHe"}],"volume":288,"language":[{"iso":"eng"}],"ddc":["000"],"date_published":"2025-06-01T00:00:00Z","publisher":"ML Research Press","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","acknowledged_ssus":[{"_id":"ScienComp"}],"file":[{"file_id":"20314","date_updated":"2025-09-09T08:10:13Z","success":1,"date_created":"2025-09-09T08:10:13Z","file_name":"2025_NeuS_Kresse.pdf","file_size":295466,"access_level":"open_access","checksum":"90a32defed34787e771a5c1623b6b0d2","creator":"dernst","content_type":"application/pdf","relation":"main_file"}],"corr_author":"1","year":"2025","title":"Logic gate neural networks are good for verification","publication_status":"published","quality_controlled":"1","file_date_updated":"2025-09-09T08:10:13Z","_id":"20296","status":"public","OA_place":"publisher","month":"06","project":[{"name":"Vigilant Algorithmic Monitoring of Software","_id":"62781420-2b32-11ec-9570-8d9b63373d4d","call_identifier":"H2020","grant_number":"101020093"}],"author":[{"last_name":"Kresse","first_name":"Fabian","full_name":"Kresse, Fabian","id":"faff3c84-23f6-11ef-9085-e5187b51c604"},{"first_name":"Zhengqi","id":"20aa2ae8-f2f1-11ed-bbfa-8205053f1342","full_name":"Yu, Zhengqi","last_name":"Yu"},{"last_name":"Lampert","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","full_name":"Lampert, Christoph","first_name":"Christoph","orcid":"0000-0001-8622-7887"},{"last_name":"Henzinger","id":"40876CD8-F248-11E8-B48F-1D18A9856A87","full_name":"Henzinger, Thomas A","first_name":"Thomas A","orcid":"0000-0002-2985-7724"}]}]