{"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/pixmix-dreamlike-pictures-comprehensively","title":"PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures","arxiv_id":"2112.05135","date":"2021-12-09","proceeding":"CVPR 2022 1","authors":["Dan Hendrycks","Andy Zou","Mantas Mazeika","Leonard Tang","Bo Li","Dawn Song","Jacob Steinhardt"],"abstract":"In real-world applications of machine learning, reliable and safe systems must consider measures of performance beyond standard test set accuracy. These other goals include out-of-distribution (OOD) robustness, prediction consistency, resilience to adversaries, calibrated uncertainty estimates, and the ability to detect anomalous inputs. However, improving performance towards these goals is often a balancing act that today's methods cannot achieve without sacrificing performance on other safety axes. For instance, adversarial training improves adversarial robustness but sharply degrades other classifier performance metrics. Similarly, strong data augmentation and regularization techniques often improve OOD robustness but harm anomaly detection, raising the question of whether a Pareto improvement on all existing safety measures is possible. To meet this challenge, we design a new data augmentation strategy utilizing the natural structural complexity of pictures such as fractals, which outperforms numerous baselines, is near Pareto-optimal, and roundly improves safety measures.","url_abs":"https://arxiv.org/abs/2112.05135v3","url_pdf":"https://arxiv.org/pdf/2112.05135v3.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":"pixmix-dreamlike-pictures-comprehensively","repo_url":"https://github.com/andyzoujm/pixmix","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"pixmix-dreamlike-pictures-comprehensively","repo_url":"https://github.com/joe1chief/windownormalizaion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"adversarial-robustness","task_name":"Adversarial Robustness"},{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2112.05135","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.05135"}},"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/andyzoujm/pixmix","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/joe1chief/windownormalizaion","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_violates":2,"ran_honours":2,"unverified":5},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":1},"listed":{"samples":5,"ran":0,"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":"190117b425ab9fe1","entry":"get_lr","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_violates","verification_level":2,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"190117b425ab9fe1"}},{"code_sha256_prefix":"9f75cd937e9f1824","entry":"float_parameter","repo":"andyzoujm/pixmix","repo_kind":"official","path":"pixmix_utils.py","file_url":"https://github.com/andyzoujm/pixmix/blob/HEAD/pixmix_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9f75cd937e9f1824"}},{"code_sha256_prefix":"fa762f2f1e10f2e4","entry":"int_parameter","repo":"andyzoujm/pixmix","repo_kind":"official","path":"pixmix_utils.py","file_url":"https://github.com/andyzoujm/pixmix/blob/HEAD/pixmix_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fa762f2f1e10f2e4"}},{"code_sha256_prefix":"5cc8d4764ac07a35","entry":"sample_level","repo":"andyzoujm/pixmix","repo_kind":"official","path":"pixmix_utils.py","file_url":"https://github.com/andyzoujm/pixmix/blob/HEAD/pixmix_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5cc8d4764ac07a35"}},{"code_sha256_prefix":"fd567f6b3711751c","entry":"calc_ins_std_mean","repo":"joe1chief/windownormalizaion","repo_kind":"listed","path":"WIN.py","file_url":"https://github.com/joe1chief/windownormalizaion/blob/HEAD/WIN.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fd567f6b3711751c"}},{"code_sha256_prefix":"a3134c82f9eca274","entry":"cn_rand_bbox","repo":"joe1chief/windownormalizaion","repo_kind":"listed","path":"WIN.py","file_url":"https://github.com/joe1chief/windownormalizaion/blob/HEAD/WIN.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a3134c82f9eca274"}},{"code_sha256_prefix":"479f80cec85ca5af","entry":"get_lr","repo":"joe1chief/windownormalizaion","repo_kind":"listed","path":"cifar.py","file_url":"https://github.com/joe1chief/windownormalizaion/blob/HEAD/cifar.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"479f80cec85ca5af"}},{"code_sha256_prefix":"2b15873947143ebd","entry":"test","repo":"joe1chief/windownormalizaion","repo_kind":"listed","path":"cifar.py","file_url":"https://github.com/joe1chief/windownormalizaion/blob/HEAD/cifar.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2b15873947143ebd"}},{"code_sha256_prefix":"eab93068178559cc","entry":"train","repo":"joe1chief/windownormalizaion","repo_kind":"listed","path":"cifar.py","file_url":"https://github.com/joe1chief/windownormalizaion/blob/HEAD/cifar.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eab93068178559cc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}