{"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/adef-an-iterative-algorithm-to-construct","title":"ADef: an Iterative Algorithm to Construct Adversarial Deformations","arxiv_id":"1804.07729","date":"2018-04-20","proceeding":"ICLR 2019 5","authors":["Rima Alaifari","Giovanni S. Alberti","Tandri Gauksson"],"abstract":"While deep neural networks have proven to be a powerful tool for many\nrecognition and classification tasks, their stability properties are still not\nwell understood. In the past, image classifiers have been shown to be\nvulnerable to so-called adversarial attacks, which are created by additively\nperturbing the correctly classified image. In this paper, we propose the ADef\nalgorithm to construct a different kind of adversarial attack created by\niteratively applying small deformations to the image, found through a gradient\ndescent step. We demonstrate our results on MNIST with convolutional neural\nnetworks and on ImageNet with Inception-v3 and ResNet-101.","url_abs":"http://arxiv.org/abs/1804.07729v3","url_pdf":"http://arxiv.org/pdf/1804.07729v3.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":"adef-an-iterative-algorithm-to-construct","repo_url":"https://github.com/MashmallowWoR/AdversarialDeformation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"adef-an-iterative-algorithm-to-construct","repo_url":"https://github.com/nicholasma88/CS260Final","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"adversarial-attack","task_name":"Adversarial Attack"},{"task_slug":"classification","task_name":"General Classification"}],"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":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"inception-v3","method_name":"Inception-v3"},{"method_slug":"inception-v3-module","method_name":"Inception-v3 Module"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"rmsprop","method_name":"RMSProp"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.07729","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.07729"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nicholasma88/CS260Final","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MashmallowWoR/AdversarialDeformation","reach":null}],"summary":{"ran_fixture":2,"ran_honours":1,"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":4,"ran":4,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"31deacf1001ce267","entry":"compose","repo":"MashmallowWoR/AdversarialDeformation","repo_kind":"listed","path":"deformation.py","file_url":"https://github.com/MashmallowWoR/AdversarialDeformation/blob/HEAD/deformation.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"31deacf1001ce267"}},{"code_sha256_prefix":"c0b68da7a768055c","entry":"eval_epoch","repo":"MashmallowWoR/AdversarialDeformation","repo_kind":"listed","path":"train_mnist.py","file_url":"https://github.com/MashmallowWoR/AdversarialDeformation/blob/HEAD/train_mnist.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c0b68da7a768055c"}},{"code_sha256_prefix":"553839a61a4e4927","entry":"gaussian_filter","repo":"MashmallowWoR/AdversarialDeformation","repo_kind":"listed","path":"deformation.py","file_url":"https://github.com/MashmallowWoR/AdversarialDeformation/blob/HEAD/deformation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"553839a61a4e4927"}},{"code_sha256_prefix":"2d22a39c619d54a0","entry":"spatial_grad","repo":"MashmallowWoR/AdversarialDeformation","repo_kind":"listed","path":"deformation.py","file_url":"https://github.com/MashmallowWoR/AdversarialDeformation/blob/HEAD/deformation.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2d22a39c619d54a0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}