{"language":[{"iso":"eng"}],"day":"26","author":[{"full_name":"Lechner, Mathias","id":"3DC22916-F248-11E8-B48F-1D18A9856A87","first_name":"Mathias","last_name":"Lechner"},{"id":"294AA7A6-F248-11E8-B48F-1D18A9856A87","full_name":"Zikelic, Dorde","orcid":"0000-0002-4681-1699","last_name":"Zikelic","first_name":"Dorde"},{"last_name":"Chatterjee","orcid":"0000-0002-4561-241X","first_name":"Krishnendu","id":"2E5DCA20-F248-11E8-B48F-1D18A9856A87","full_name":"Chatterjee, Krishnendu"},{"first_name":"Thomas A","last_name":"Henzinger","orcid":"0000-0002-2985-7724","full_name":"Henzinger, Thomas A","id":"40876CD8-F248-11E8-B48F-1D18A9856A87"},{"full_name":"Rus, Daniela","first_name":"Daniela","last_name":"Rus"}],"main_file_link":[{"open_access":"1","url":"https://doi.org/10.48550/arXiv.2211.16187"}],"page":"14964-14973","oa":1,"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."}],"year":"2023","quality_controlled":"1","volume":37,"date_published":"2023-06-26T00:00:00Z","scopus_import":"1","article_processing_charge":"No","title":"Quantization-aware interval bound propagation for training certifiably robust quantized neural networks","intvolume":"        37","citation":{"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.","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.","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>","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>","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."},"publication_identifier":{"isbn":["9781577358800"]},"publication":"Proceedings of the 37th AAAI Conference on Artificial Intelligence","issue":"12","month":"06","date_created":"2023-08-27T22:01:17Z","publication_status":"published","publisher":"Association for the Advancement of Artificial Intelligence","external_id":{"arxiv":["2211.16187"]},"conference":{"name":"AAAI: Conference on Artificial Intelligence","start_date":"2023-02-07","end_date":"2023-02-14","location":"Washington, DC, United States"},"status":"public","_id":"14242","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.","ec_funded":1,"oa_version":"Preprint","department":[{"_id":"ToHe"},{"_id":"KrCh"}],"doi":"10.1609/aaai.v37i12.26747","project":[{"grant_number":"101020093","call_identifier":"H2020","name":"Vigilant Algorithmic Monitoring of Software","_id":"62781420-2b32-11ec-9570-8d9b63373d4d"},{"grant_number":"863818","call_identifier":"H2020","_id":"0599E47C-7A3F-11EA-A408-12923DDC885E","name":"Formal Methods for Stochastic Models: Algorithms and Applications"},{"grant_number":"665385","call_identifier":"H2020","_id":"2564DBCA-B435-11E9-9278-68D0E5697425","name":"International IST Doctoral Program"}],"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","date_updated":"2023-09-05T07:06:14Z","type":"conference"}