{"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-generative-nets-neural-network","title":"A General Framework for Adversarial Examples with Objectives","arxiv_id":"1801.00349","date":"2017-12-31","proceeding":null,"authors":["Mahmood Sharif","Sruti Bhagavatula","Lujo Bauer","Michael K. Reiter"],"abstract":"Images perturbed subtly to be misclassified by neural networks, called\nadversarial examples, have emerged as a technically deep challenge and an\nimportant concern for several application domains. Most research on adversarial\nexamples takes as its only constraint that the perturbed images are similar to\nthe originals. However, real-world application of these ideas often requires\nthe examples to satisfy additional objectives, which are typically enforced\nthrough custom modifications of the perturbation process. In this paper, we\npropose adversarial generative nets (AGNs), a general methodology to train a\ngenerator neural network to emit adversarial examples satisfying desired\nobjectives. We demonstrate the ability of AGNs to accommodate a wide range of\nobjectives, including imprecise ones difficult to model, in two application\ndomains. In particular, we demonstrate physical adversarial examples---eyeglass\nframes designed to fool face recognition---with better robustness,\ninconspicuousness, and scalability than previous approaches, as well as a new\nattack to fool a handwritten-digit classifier.","url_abs":"http://arxiv.org/abs/1801.00349v2","url_pdf":"http://arxiv.org/pdf/1801.00349v2.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-generative-nets-neural-network","repo_url":"https://github.com/mahmoods01/agns","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"adversarial-generative-nets-neural-network","repo_url":"https://github.com/drewbarot/Un-CNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"adversarial-generative-nets-neural-network","repo_url":"https://github.com/jchaykow/AGN-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"face-recognition","task_name":"Face Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1801.00349","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1801.00349"}},"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/drewbarot/Un-CNN","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mahmoods01/agns","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jchaykow/AGN-pytorch","reach":null}],"summary":{"ran_honours":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"ea1e24a9e203ea47","entry":"unorm_glasses","repo":"jchaykow/AGN-pytorch","repo_kind":"listed","path":"video_inference_cv.py","file_url":"https://github.com/jchaykow/AGN-pytorch/blob/HEAD/video_inference_cv.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ea1e24a9e203ea47"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}