[{"status":"public","type":"conference","arxiv":1,"author":[{"last_name":"Lechner","id":"3DC22916-F248-11E8-B48F-1D18A9856A87","full_name":"Lechner, Mathias","first_name":"Mathias"},{"full_name":"Zikelic, Dorde","first_name":"Dorde","orcid":"0000-0002-4681-1699","id":"294AA7A6-F248-11E8-B48F-1D18A9856A87","last_name":"Zikelic"},{"id":"2E5DCA20-F248-11E8-B48F-1D18A9856A87","last_name":"Chatterjee","orcid":"0000-0002-4561-241X","full_name":"Chatterjee, Krishnendu","first_name":"Krishnendu"},{"full_name":"Henzinger, Thomas A","first_name":"Thomas A","last_name":"Henzinger","id":"40876CD8-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0002-2985-7724"},{"full_name":"Rus, Daniela","first_name":"Daniela","last_name":"Rus"}],"month":"06","publication_identifier":{"isbn":["9781577358800"]},"conference":{"name":"AAAI: Conference on Artificial Intelligence","start_date":"2023-02-07","location":"Washington, DC, United States","end_date":"2023-02-14"},"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","day":"26","main_file_link":[{"open_access":"1","url":"https://doi.org/10.48550/arXiv.2211.16187"}],"oa_version":"Preprint","language":[{"iso":"eng"}],"publication":"Proceedings of the 37th AAAI Conference on Artificial Intelligence","article_processing_charge":"No","issue":"12","oa":1,"date_updated":"2025-07-14T09:09:56Z","title":"Quantization-aware interval bound propagation for training certifiably robust quantized neural networks","intvolume":"        37","scopus_import":"1","project":[{"name":"Vigilant Algorithmic Monitoring of Software","call_identifier":"H2020","_id":"62781420-2b32-11ec-9570-8d9b63373d4d","grant_number":"101020093"},{"name":"Formal Methods for Stochastic Models: Algorithms and Applications","call_identifier":"H2020","_id":"0599E47C-7A3F-11EA-A408-12923DDC885E","grant_number":"863818"},{"name":"International IST Doctoral Program","call_identifier":"H2020","_id":"2564DBCA-B435-11E9-9278-68D0E5697425","grant_number":"665385"}],"date_published":"2023-06-26T00:00:00Z","publisher":"Association for the Advancement of Artificial Intelligence","quality_controlled":"1","volume":37,"page":"14964-14973","department":[{"_id":"ToHe"},{"_id":"KrCh"}],"publication_status":"published","abstract":[{"lang":"eng","text":"We study the problem of training and certifying adversarially robust quantized neural networks (QNNs). Quantization is a technique for making neural networks more efficient by running them using low-bit integer arithmetic and is therefore commonly adopted in industry. Recent work has shown that floating-point neural networks that have been verified to be robust can become vulnerable to adversarial attacks after quantization, and certification of the quantized representation is necessary to guarantee robustness. In this work, we present quantization-aware interval bound propagation (QA-IBP), a novel method for training robust QNNs. Inspired by advances in robust learning of non-quantized networks, our training algorithm computes the gradient of an abstract representation of the actual network. Unlike existing approaches, our method can handle the discrete semantics of QNNs. Based on QA-IBP, we also develop a complete verification procedure for verifying the adversarial robustness of QNNs, which is guaranteed to terminate and produce a correct answer. Compared to existing approaches, the key advantage of our verification procedure is that it runs entirely on GPU or other accelerator devices. We demonstrate experimentally that our approach significantly outperforms existing methods and establish the new state-of-the-art for training and certifying the robustness of QNNs."}],"external_id":{"arxiv":["2211.16187"]},"_id":"14242","doi":"10.1609/aaai.v37i12.26747","year":"2023","acknowledgement":"This work was supported in part by the ERC-2020-AdG 101020093, ERC CoG 863818 (FoRM-SMArt) and the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie Grant Agreement No. 665385. Research was sponsored by the United\r\nStates Air Force Research Laboratory and the United States Air Force Artificial Intelligence Accelerator and was accomplished under Cooperative Agreement Number FA8750-19-2-\r\n1000. The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied,\r\nof the United States Air Force or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright\r\nnotation herein. The research was also funded in part by the AI2050 program at Schmidt Futures (Grant G-22-63172) and Capgemini SE.","citation":{"apa":"Lechner, M., Zikelic, D., Chatterjee, K., Henzinger, T. A., &#38; Rus, D. (2023). Quantization-aware interval bound propagation for training certifiably robust quantized neural networks. In <i>Proceedings of the 37th AAAI Conference on Artificial Intelligence</i> (Vol. 37, pp. 14964–14973). Washington, DC, United States: Association for the Advancement of Artificial Intelligence. <a href=\"https://doi.org/10.1609/aaai.v37i12.26747\">https://doi.org/10.1609/aaai.v37i12.26747</a>","short":"M. Lechner, D. Zikelic, K. Chatterjee, T.A. Henzinger, D. Rus, in:, Proceedings of the 37th AAAI Conference on Artificial Intelligence, Association for the Advancement of Artificial Intelligence, 2023, pp. 14964–14973.","ieee":"M. Lechner, D. Zikelic, K. Chatterjee, T. A. Henzinger, and D. Rus, “Quantization-aware interval bound propagation for training certifiably robust quantized neural networks,” in <i>Proceedings of the 37th AAAI Conference on Artificial Intelligence</i>, Washington, DC, United States, 2023, vol. 37, no. 12, pp. 14964–14973.","ama":"Lechner M, Zikelic D, Chatterjee K, Henzinger TA, Rus D. Quantization-aware interval bound propagation for training certifiably robust quantized neural networks. In: <i>Proceedings of the 37th AAAI Conference on Artificial Intelligence</i>. Vol 37. Association for the Advancement of Artificial Intelligence; 2023:14964-14973. doi:<a href=\"https://doi.org/10.1609/aaai.v37i12.26747\">10.1609/aaai.v37i12.26747</a>","chicago":"Lechner, Mathias, Dorde Zikelic, Krishnendu Chatterjee, Thomas A Henzinger, and Daniela Rus. “Quantization-Aware Interval Bound Propagation for Training Certifiably Robust Quantized Neural Networks.” In <i>Proceedings of the 37th AAAI Conference on Artificial Intelligence</i>, 37:14964–73. Association for the Advancement of Artificial Intelligence, 2023. <a href=\"https://doi.org/10.1609/aaai.v37i12.26747\">https://doi.org/10.1609/aaai.v37i12.26747</a>.","mla":"Lechner, Mathias, et al. “Quantization-Aware Interval Bound Propagation for Training Certifiably Robust Quantized Neural Networks.” <i>Proceedings of the 37th AAAI Conference on Artificial Intelligence</i>, vol. 37, no. 12, Association for the Advancement of Artificial Intelligence, 2023, pp. 14964–73, doi:<a href=\"https://doi.org/10.1609/aaai.v37i12.26747\">10.1609/aaai.v37i12.26747</a>.","ista":"Lechner M, Zikelic D, Chatterjee K, Henzinger TA, Rus D. 2023. Quantization-aware interval bound propagation for training certifiably robust quantized neural networks. Proceedings of the 37th AAAI Conference on Artificial Intelligence. AAAI: Conference on Artificial Intelligence vol. 37, 14964–14973."},"date_created":"2023-08-27T22:01:17Z","ec_funded":1},{"type":"conference","status":"public","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","main_file_link":[{"url":"https://doi.org/10.1609/aaai.v37i5.25679","open_access":"1"}],"day":"27","oa_version":"Published Version","month":"06","publication_identifier":{"isbn":["9781577358800"]},"conference":{"end_date":"2023-02-14","location":"Washington, DC, United States","start_date":"2023-02-07","name":"AAAI: Conference on Artificial Intelligence"},"arxiv":1,"author":[{"full_name":"Avni, Guy","first_name":"Guy","last_name":"Avni","id":"463C8BC2-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0001-5588-8287"},{"id":"85D7C63E-7D5D-11E9-9C0F-98C4E5697425","last_name":"Jecker","full_name":"Jecker, Ismael R","first_name":"Ismael R"},{"last_name":"Zikelic","id":"294AA7A6-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0002-4681-1699","full_name":"Zikelic, Dorde","first_name":"Dorde"}],"publication":"Proceedings of the 37th AAAI Conference on Artificial Intelligence","language":[{"iso":"eng"}],"intvolume":"        37","scopus_import":"1","title":"Bidding graph games with partially-observable budgets","issue":"5","article_processing_charge":"No","date_updated":"2025-07-14T09:09:56Z","oa":1,"quality_controlled":"1","volume":37,"page":"5464-5471","department":[{"_id":"ToHe"},{"_id":"KrCh"}],"date_published":"2023-06-27T00:00:00Z","project":[{"_id":"0599E47C-7A3F-11EA-A408-12923DDC885E","grant_number":"863818","name":"Formal Methods for Stochastic Models: Algorithms and Applications","call_identifier":"H2020"},{"call_identifier":"H2020","name":"International IST Doctoral Program","grant_number":"665385","_id":"2564DBCA-B435-11E9-9278-68D0E5697425"}],"abstract":[{"text":"Two-player zero-sum \"graph games\" are central in logic, verification, and multi-agent systems. The game proceeds by placing a token on a vertex of a graph, and allowing the players to move it to produce an infinite path, which determines the winner or payoff of the game. Traditionally, the players alternate turns in moving the token. In \"bidding games\", however, the players have budgets and in each turn, an auction (bidding) determines which player moves the token. So far, bidding games have only been studied as full-information games. In this work we initiate the study of partial-information bidding games: we study bidding games in which a player's initial budget is drawn from a known probability distribution. We show that while for some bidding mechanisms and objectives, it is straightforward to adapt the results from the full-information setting to the partial-information setting, for others, the analysis is significantly more challenging, requires new techniques, and gives rise to interesting results. Specifically, we study games with \"mean-payoff\" objectives in combination with \"poorman\" bidding. We construct optimal strategies for a partially-informed player who plays against a fully-informed adversary. We show that, somewhat surprisingly, the \"value\" under pure strategies does not necessarily exist in such games.","lang":"eng"}],"external_id":{"arxiv":["2211.13626"]},"publication_status":"published","doi":"10.1609/aaai.v37i5.25679","_id":"14243","ec_funded":1,"date_created":"2023-08-27T22:01:18Z","citation":{"apa":"Avni, G., Jecker, I. R., &#38; Zikelic, D. (2023). Bidding graph games with partially-observable budgets. In <i>Proceedings of the 37th AAAI Conference on Artificial Intelligence</i> (Vol. 37, pp. 5464–5471). Washington, DC, United States. <a href=\"https://doi.org/10.1609/aaai.v37i5.25679\">https://doi.org/10.1609/aaai.v37i5.25679</a>","ama":"Avni G, Jecker IR, Zikelic D. Bidding graph games with partially-observable budgets. In: <i>Proceedings of the 37th AAAI Conference on Artificial Intelligence</i>. Vol 37. ; 2023:5464-5471. doi:<a href=\"https://doi.org/10.1609/aaai.v37i5.25679\">10.1609/aaai.v37i5.25679</a>","ieee":"G. Avni, I. R. Jecker, and D. Zikelic, “Bidding graph games with partially-observable budgets,” in <i>Proceedings of the 37th AAAI Conference on Artificial Intelligence</i>, Washington, DC, United States, 2023, vol. 37, no. 5, pp. 5464–5471.","short":"G. Avni, I.R. Jecker, D. Zikelic, in:, Proceedings of the 37th AAAI Conference on Artificial Intelligence, 2023, pp. 5464–5471.","ista":"Avni G, Jecker IR, Zikelic D. 2023. Bidding graph games with partially-observable budgets. Proceedings of the 37th AAAI Conference on Artificial Intelligence. AAAI: Conference on Artificial Intelligence vol. 37, 5464–5471.","mla":"Avni, Guy, et al. “Bidding Graph Games with Partially-Observable Budgets.” <i>Proceedings of the 37th AAAI Conference on Artificial Intelligence</i>, vol. 37, no. 5, 2023, pp. 5464–71, doi:<a href=\"https://doi.org/10.1609/aaai.v37i5.25679\">10.1609/aaai.v37i5.25679</a>.","chicago":"Avni, Guy, Ismael R Jecker, and Dorde Zikelic. “Bidding Graph Games with Partially-Observable Budgets.” In <i>Proceedings of the 37th AAAI Conference on Artificial Intelligence</i>, 37:5464–71, 2023. <a href=\"https://doi.org/10.1609/aaai.v37i5.25679\">https://doi.org/10.1609/aaai.v37i5.25679</a>."},"year":"2023","acknowledgement":"This research was supported in part by ISF grant no.1679/21, by the ERC CoG 863818 (ForM-SMArt), and the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie Grant Agreement No. 665385."}]