{"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/on-extensions-of-clever-a-neural-network","title":"On Extensions of CLEVER: A Neural Network Robustness Evaluation Algorithm","arxiv_id":"1810.08640","date":"2018-10-19","proceeding":null,"authors":["Tsui-Wei Weng","huan zhang","Pin-Yu Chen","Aurelie Lozano","Cho-Jui Hsieh","Luca Daniel"],"abstract":"CLEVER (Cross-Lipschitz Extreme Value for nEtwork Robustness) is an Extreme\nValue Theory (EVT) based robustness score for large-scale deep neural networks\n(DNNs). In this paper, we propose two extensions on this robustness score.\nFirst, we provide a new formal robustness guarantee for classifier functions\nthat are twice differentiable. We apply extreme value theory on the new formal\nrobustness guarantee and the estimated robustness is called second-order CLEVER\nscore. Second, we discuss how to handle gradient masking, a common defensive\ntechnique, using CLEVER with Backward Pass Differentiable Approximation (BPDA).\nWith BPDA applied, CLEVER can evaluate the intrinsic robustness of neural\nnetworks of a broader class -- networks with non-differentiable input\ntransformations. We demonstrate the effectiveness of CLEVER with BPDA in\nexperiments on a 121-layer Densenet model trained on the ImageNet dataset.","url_abs":"http://arxiv.org/abs/1810.08640v1","url_pdf":"http://arxiv.org/pdf/1810.08640v1.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":"on-extensions-of-clever-a-neural-network","repo_url":"https://github.com/huanzhang12/CLEVER","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-block","method_name":"Dense Block"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"softmax","method_name":"Softmax"}],"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}