{"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-examples-in-the-physical-world","title":"Adversarial examples in the physical world","arxiv_id":"1607.02533","date":"2016-07-08","proceeding":null,"authors":["Alexey Kurakin","Ian Goodfellow","Samy Bengio"],"abstract":"Most existing machine learning classifiers are highly vulnerable to\nadversarial examples. An adversarial example is a sample of input data which\nhas been modified very slightly in a way that is intended to cause a machine\nlearning classifier to misclassify it. In many cases, these modifications can\nbe so subtle that a human observer does not even notice the modification at\nall, yet the classifier still makes a mistake. Adversarial examples pose\nsecurity concerns because they could be used to perform an attack on machine\nlearning systems, even if the adversary has no access to the underlying model.\nUp to now, all previous work have assumed a threat model in which the adversary\ncan feed data directly into the machine learning classifier. This is not always\nthe case for systems operating in the physical world, for example those which\nare using signals from cameras and other sensors as an input. This paper shows\nthat even in such physical world scenarios, machine learning systems are\nvulnerable to adversarial examples. We demonstrate this by feeding adversarial\nimages obtained from cell-phone camera to an ImageNet Inception classifier and\nmeasuring the classification accuracy of the system. We find that a large\nfraction of adversarial examples are classified incorrectly even when perceived\nthrough the camera.","url_abs":"http://arxiv.org/abs/1607.02533v4","url_pdf":"http://arxiv.org/pdf/1607.02533v4.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-examples-in-the-physical-world","repo_url":"https://github.com/1Konny/FGSM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"adversarial-examples-in-the-physical-world","repo_url":"https://github.com/Trustworthy-AI-Group/TransferAttack","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"adversarial-examples-in-the-physical-world","repo_url":"https://github.com/as791/Adversarial-Example-Attack-and-Defense","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok"}},{"paper_slug":"adversarial-examples-in-the-physical-world","repo_url":"https://github.com/harry24k/aepw-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"adversarial-examples-in-the-physical-world","repo_url":"https://github.com/jaesik817/adv_attack_capsnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"adversarial-examples-in-the-physical-world","repo_url":"https://github.com/niazarak/adversarial-attack","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1607.02533","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1607.02533"}},"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/Trustworthy-AI-Group/TransferAttack","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jaesik817/adv_attack_capsnet","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/harry24k/aepw-pytorch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/as791/Adversarial-Example-Attack-and-Defense","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/1Konny/FGSM","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/niazarak/adversarial-attack","reach":null}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"listed":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"62ca13b288fb7f80","entry":"clip","repo":"niazarak/adversarial-attack","repo_kind":"listed","path":"adversarial.py","file_url":"https://github.com/niazarak/adversarial-attack/blob/HEAD/adversarial.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"62ca13b288fb7f80"}},{"code_sha256_prefix":"255735430fc0631b","entry":"train_adv_examples","repo":"niazarak/adversarial-attack","repo_kind":"listed","path":"adversarial.py","file_url":"https://github.com/niazarak/adversarial-attack/blob/HEAD/adversarial.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"255735430fc0631b"}},{"code_sha256_prefix":"35828f5ef17691fd","entry":"train_adv_fgsm","repo":"niazarak/adversarial-attack","repo_kind":"listed","path":"adversarial.py","file_url":"https://github.com/niazarak/adversarial-attack/blob/HEAD/adversarial.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"35828f5ef17691fd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}