{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/certifying-geometric-robustness-of-neural","title":"Certifying Geometric Robustness of Neural Networks","arxiv_id":null,"date":"2019-12-01","proceeding":"NeurIPS 2019 12","authors":["Mislav Balunovic","Maximilian Baader","Gagandeep Singh","Timon Gehr","Martin Vechev"],"abstract":"The use of neural networks in safety-critical computer vision systems calls for their\nrobustness certification against natural geometric transformations (e.g., rotation,\nscaling). However, current certification methods target mostly norm-based pixel\nperturbations and cannot certify robustness against geometric transformations. In\nthis work, we propose a new method to compute sound and asymptotically optimal\nlinear relaxations for any composition of transformations. Our method is based on\na novel combination of sampling and optimization. We implemented the method\nin a system called DeepG and demonstrated that it certifies significantly more\ncomplex geometric transformations than existing methods on both defended and\nundefended networks while scaling to large architectures.","url_abs":"http://papers.nips.cc/paper/9666-certifying-geometric-robustness-of-neural-networks","url_pdf":"http://papers.nips.cc/paper/9666-certifying-geometric-robustness-of-neural-networks.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"certifying-geometric-robustness-of-neural","repo_url":"https://github.com/eth-sri/deepg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}