{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/on-the-effectiveness-of-interval-bound","title":"On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models","arxiv_id":"1810.12715","date":"2018-10-30","proceeding":null,"authors":["Sven Gowal","Krishnamurthy Dvijotham","Robert Stanforth","Rudy Bunel","Chongli Qin","Jonathan Uesato","Relja Arandjelovic","Timothy Mann","Pushmeet Kohli"],"abstract":"Recent work has shown that it is possible to train deep neural networks that are provably robust to norm-bounded adversarial perturbations. Most of these methods are based on minimizing an upper bound on the worst-case loss over all possible adversarial perturbations. While these techniques show promise, they often result in difficult optimization procedures that remain hard to scale to larger networks. Through a comprehensive analysis, we show how a simple bounding technique, interval bound propagation (IBP), can be exploited to train large provably robust neural networks that beat the state-of-the-art in verified accuracy. While the upper bound computed by IBP can be quite weak for general networks, we demonstrate that an appropriate loss and clever hyper-parameter schedule allow the network to adapt such that the IBP bound is tight. This results in a fast and stable learning algorithm that outperforms more sophisticated methods and achieves state-of-the-art results on MNIST, CIFAR-10 and SVHN. It also allows us to train the largest model to be verified beyond vacuous bounds on a downscaled version of ImageNet.","url_abs":"https://arxiv.org/abs/1810.12715v4","url_pdf":"https://arxiv.org/pdf/1810.12715v4.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":"on-the-effectiveness-of-interval-bound","repo_url":"https://github.com/deepmind/interval-bound-propagation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"on-the-effectiveness-of-interval-bound","repo_url":"https://github.com/Ping-C/certifiedpatchdefense","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"on-the-effectiveness-of-interval-bound","repo_url":"https://github.com/eth-sri/diffai","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"on-the-effectiveness-of-interval-bound","repo_url":"https://github.com/huanzhang12/CROWN-IBP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"paper_slug":"on-the-effectiveness-of-interval-bound","repo_url":"https://github.com/j-cb/GOOD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"on-the-effectiveness-of-interval-bound","repo_url":"https://github.com/kyleliang919/Interval-bound-propagation-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"on-the-effectiveness-of-interval-bound","repo_url":"https://github.com/pawelmorawiecki/Interval_bound_propagation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"on-the-effectiveness-of-interval-bound","repo_url":"https://github.com/sungyoon-lee/bcp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"on-the-effectiveness-of-interval-bound","repo_url":"https://gitlab.com/Bitterwolf/GOOD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1810.12715","atlas_url":"https://app.syntology.ai/?focus=1810.12715","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.12715"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1810.12715"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1810.12715"},"call":"get_harvested_code_for_paper(arxiv_id=\"1810.12715\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"1810.12715"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1810.12715\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1810.12715"},"call":"get_concepts_for_paper(arxiv_id=\"1810.12715\")"}],"by_repo":[{"repo":"deepmind/interval-bound-propagation","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1909.01492"],"harvested_for_calls":[{"arxiv_id":"1909.01492","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1909.01492"},"call":"get_harvested_code_for_paper(arxiv_id=\"1909.01492\")"}]},{"repo":"Ping-C/certifiedpatchdefense","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2003.06693"],"harvested_for_calls":[{"arxiv_id":"2003.06693","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2003.06693"},"call":"get_harvested_code_for_paper(arxiv_id=\"2003.06693\")"}]},{"repo":"eth-sri/diffai","kind":"listed","samples":3,"ran":1,"instrument":1,"unverified":2,"placed_by_identical_code":3},{"repo":"huanzhang12/CROWN-IBP","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2002.12920"],"harvested_for_calls":[{"arxiv_id":"2002.12920","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2002.12920"},"call":"get_harvested_code_for_paper(arxiv_id=\"2002.12920\")"}]},{"repo":"j-cb/GOOD","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"kyleliang919/Interval-bound-propagation-pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"pawelmorawiecki/Interval_bound_propagation","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"sungyoon-lee/bcp","kind":"listed","samples":3,"ran":2,"instrument":0,"unverified":1},{"repo":"gitlab.com/Bitterwolf/GOOD","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/1810.12715.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/1810.12715.svg"},"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/pawelmorawiecki/Interval_bound_propagation","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/eth-sri/diffai","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kyleliang919/Interval-bound-propagation-pytorch","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/huanzhang12/CROWN-IBP","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sungyoon-lee/bcp","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Ping-C/certifiedpatchdefense","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://gitlab.com/Bitterwolf/GOOD","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/deepmind/interval-bound-propagation","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/j-cb/GOOD","reach":{"status":"ok"}}],"summary":{"ran":2,"ran_draft_wrong":1,"unverified":3},"n_samples":6,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":3,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"listed":{"samples":6,"ran":3,"n_ran_checked":2,"n_instrument":1,"repositories":2}},"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"},"official_not_harvested":{"repositories":["deepmind/interval-bound-propagation"],"harvested_for_other_papers":[1],"samples_from_other_repositories":6,"other_repositories":2,"samples_unlocated":0},"n_pointer_only_for_licence":3,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":3,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-26","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"846b8ce1a0cef2b3","code_sha256_prefix":"846b8ce1a0cef2b3","entry":"argparser","repo":"sungyoon-lee/bcp","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/sungyoon-lee/bcp/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"data:str/0/str, model:str/0/str, batch_size:int/0/int, epochs:int/0/int, warmup:int/0/int, rampup:int/0/int, augmentation:bool/0/bool, seed:int/0/int, verbose:int/0/int, epsilon:float/0/float, epsilon_infty:float/0/float, epsilon_train:float/0/float, epsilon_train_infty:float/0/float, starting_epsilon:float/0/float, opt:str/0/str, lr:float/0/float, momentum:float/0/float, weight_decay:float/0/float, step_size:int/0/int, gamma:float/0/float, lr_scheduler:str/0/str, wd_list:NoneType/0/?, starting_kappa:float/0/float, kappa:float/0/float, niter:int/0/int, opt_iter:int/0/int, sniter:int/0/int, test_opt_iter:int/0/int, test_sniter:int/0/int","fixture_out_type":"Namespace","level_recorded_at":"2026-09-26T05:30:53.715539+00:00","code_page":"/code/argparser","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"846b8ce1a0cef2b3"}},{"code_sha256":"f8f37cd8a52870c1","code_sha256_prefix":"f8f37cd8a52870c1","entry":"catNonNullErrors","repo":null,"repo_kind":"listed","path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"op:callable/0/?, ref_errs:Tensor/1/float","fixture_out_type":"function","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"placed_by_identical_code":{"repo":"eth-sri/diffai","path":"ai.py","file_url":"https://github.com/eth-sri/diffai/blob/HEAD/ai.py","papers":["1412.6572"],"is":"identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own"},"licence":null,"inline_ok":false,"inline_ok_link":false,"withheld_clause":"this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it","mcp_get_code":{"code_sha256":"f8f37cd8a52870c1"}},{"code_sha256":"fb45ae0df896c8db","code_sha256_prefix":"fb45ae0df896c8db","entry":"model_cnn_4layer","repo":"sungyoon-lee/bcp","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/sungyoon-lee/bcp/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"in_ch:int/0/int, in_dim:int/0/int, width:int/0/int, linear_size:int/0/int","fixture_out_type":"Sequential","level_recorded_at":"2026-09-26T05:00:14.332320+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"fb45ae0df896c8db"}},{"code_sha256":"a49c0dd16152c346","code_sha256_prefix":"a49c0dd16152c346","entry":"creluBoxy","repo":null,"repo_kind":"listed","path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"placed_by_identical_code":{"repo":"eth-sri/diffai","path":"ai.py","file_url":"https://github.com/eth-sri/diffai/blob/HEAD/ai.py","papers":["1412.6572"],"is":"identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own"},"licence":null,"inline_ok":false,"inline_ok_link":false,"withheld_clause":"this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it","mcp_get_code":{"code_sha256":"a49c0dd16152c346"}},{"code_sha256":"c42ef7b9012126aa","code_sha256_prefix":"c42ef7b9012126aa","entry":"creluBoxySound","repo":null,"repo_kind":"listed","path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"placed_by_identical_code":{"repo":"eth-sri/diffai","path":"ai.py","file_url":"https://github.com/eth-sri/diffai/blob/HEAD/ai.py","papers":["1412.6572"],"is":"identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own"},"licence":null,"inline_ok":false,"inline_ok_link":false,"withheld_clause":"this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it","mcp_get_code":{"code_sha256":"c42ef7b9012126aa"}},{"code_sha256":"bb465636abefa4b4","code_sha256_prefix":"bb465636abefa4b4","entry":"select_model","repo":"sungyoon-lee/bcp","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/sungyoon-lee/bcp/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/select-model","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"bb465636abefa4b4"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"da92f00b28254d56016206d9dbf3fcca1bee7630e08867475d0cd54a1ecf7d5c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}