{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T04:28:31Z","timestamp":1729225711383,"version":"3.27.0"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643685489","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T00:00:00Z","timestamp":1729036800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,16]]},"abstract":"<jats:p>We address the problem of verifying neural networks against geometric transformations of the input image, including rotation, scaling, shearing, and translation. The proposed method computes provably sound piecewise linear constraints for the pixel values by using sampling and linear approximations in combination with branch-and-bound Lipschitz optimisation. The method obtains provably tighter over-approximations of the perturbation region than the present state-of-the-art. We report results from experiments on a comprehensive set of verification benchmarks on MNIST and CIFAR10. We show that our proposed implementation resolves up to 32% more verification cases than present approaches.<\/jats:p>","DOI":"10.3233\/faia240761","type":"book-chapter","created":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T13:19:21Z","timestamp":1729171161000},"source":"Crossref","is-referenced-by-count":0,"title":["Verification of Geometric Robustness of Neural Networks via Piecewise Linear Approximation and Lipschitz Optimisation"],"prefix":"10.3233","author":[{"given":"Ben","family":"Batten","sequence":"first","affiliation":[{"name":"Imperial College London, UK"}]},{"given":"Yang","family":"Zheng","sequence":"additional","affiliation":[{"name":"University of California San Diego, USA"}]},{"given":"Alessandro","family":"De Palma","sequence":"additional","affiliation":[{"name":"Inria, \u00c9cole Normale Sup\u00e9rieure, PSL University, CNRS, France"}]},{"given":"Panagiotis","family":"Kouvaros","sequence":"additional","affiliation":[{"name":"Safe Intelligence, UK"},{"name":"Department of Information Technologies, University of Limassol, Cyprus"}]},{"given":"Alessio","family":"Lomuscio","sequence":"additional","affiliation":[{"name":"Imperial College London, UK"},{"name":"Safe Intelligence, UK"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","ECAI 2024"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA240761","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T13:19:22Z","timestamp":1729171162000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA240761"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,16]]},"ISBN":["9781643685489"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia240761","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,16]]}}}