{"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/evaluating-the-robustness-of-neural-networks","title":"Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach","arxiv_id":"1801.10578","date":"2018-01-31","proceeding":"ICLR 2018 1","authors":["Tsui-Wei Weng","huan zhang","Pin-Yu Chen","Jin-Feng Yi","Dong Su","Yupeng Gao","Cho-Jui Hsieh","Luca Daniel"],"abstract":"The robustness of neural networks to adversarial examples has received great\nattention due to security implications. Despite various attack approaches to\ncrafting visually imperceptible adversarial examples, little has been developed\ntowards a comprehensive measure of robustness. In this paper, we provide a\ntheoretical justification for converting robustness analysis into a local\nLipschitz constant estimation problem, and propose to use the Extreme Value\nTheory for efficient evaluation. Our analysis yields a novel robustness metric\ncalled CLEVER, which is short for Cross Lipschitz Extreme Value for nEtwork\nRobustness. The proposed CLEVER score is attack-agnostic and computationally\nfeasible for large neural networks. Experimental results on various networks,\nincluding ResNet, Inception-v3 and MobileNet, show that (i) CLEVER is aligned\nwith the robustness indication measured by the $\\ell_2$ and $\\ell_\\infty$ norms\nof adversarial examples from powerful attacks, and (ii) defended networks using\ndefensive distillation or bounded ReLU indeed achieve better CLEVER scores. To\nthe best of our knowledge, CLEVER is the first attack-independent robustness\nmetric that can be applied to any neural network classifier.","url_abs":"http://arxiv.org/abs/1801.10578v1","url_pdf":"http://arxiv.org/pdf/1801.10578v1.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":"evaluating-the-robustness-of-neural-networks","repo_url":"https://github.com/huanzhang12/CLEVER","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"auxiliary-classifier","method_name":"Auxiliary Classifier"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"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":"inception-v3","method_name":"Inception-v3"},{"method_slug":"inception-v3-module","method_name":"Inception-v3 Module"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"rmsprop","method_name":"RMSProp"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1801.10578","atlas_url":"https://app.syntology.ai/?focus=1801.10578","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}