{"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/adversarial-transformation-networks-learning","title":"Adversarial Transformation Networks: Learning to Generate Adversarial Examples","arxiv_id":"1703.09387","date":"2017-03-28","proceeding":null,"authors":["Shumeet Baluja","Ian Fischer"],"abstract":"Multiple different approaches of generating adversarial examples have been\nproposed to attack deep neural networks. These approaches involve either\ndirectly computing gradients with respect to the image pixels, or directly\nsolving an optimization on the image pixels. In this work, we present a\nfundamentally new method for generating adversarial examples that is fast to\nexecute and provides exceptional diversity of output. We efficiently train\nfeed-forward neural networks in a self-supervised manner to generate\nadversarial examples against a target network or set of networks. We call such\na network an Adversarial Transformation Network (ATN). ATNs are trained to\ngenerate adversarial examples that minimally modify the classifier's outputs\ngiven the original input, while constraining the new classification to match an\nadversarial target class. We present methods to train ATNs and analyze their\neffectiveness targeting a variety of MNIST classifiers as well as the latest\nstate-of-the-art ImageNet classifier Inception ResNet v2.","url_abs":"http://arxiv.org/abs/1703.09387v1","url_pdf":"http://arxiv.org/pdf/1703.09387v1.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":"adversarial-transformation-networks-learning","repo_url":"https://github.com/cs-giung/course-dl-TP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"adversarial-transformation-networks-learning","repo_url":"https://github.com/pfnet-research/nips17-adversarial-attack","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"}],"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":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"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":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1703.09387","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}