{"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/collider-a-robust-training-framework-for","title":"COLLIDER: A Robust Training Framework for Backdoor Data","arxiv_id":"2210.06704","date":"2022-10-13","proceeding":null,"authors":["Hadi M. Dolatabadi","Sarah Erfani","Christopher Leckie"],"abstract":"Deep neural network (DNN) classifiers are vulnerable to backdoor attacks. An adversary poisons some of the training data in such attacks by installing a trigger. The goal is to make the trained DNN output the attacker's desired class whenever the trigger is activated while performing as usual for clean data. Various approaches have recently been proposed to detect malicious backdoored DNNs. However, a robust, end-to-end training approach, like adversarial training, is yet to be discovered for backdoor poisoned data. In this paper, we take the first step toward such methods by developing a robust training framework, COLLIDER, that selects the most prominent samples by exploiting the underlying geometric structures of the data. Specifically, we effectively filter out candidate poisoned data at each training epoch by solving a geometrical coreset selection objective. We first argue how clean data samples exhibit (1) gradients similar to the clean majority of data and (2) low local intrinsic dimensionality (LID). Based on these criteria, we define a novel coreset selection objective to find such samples, which are used for training a DNN. We show the effectiveness of the proposed method for robust training of DNNs on various poisoned datasets, reducing the backdoor success rate significantly.","url_abs":"https://arxiv.org/abs/2210.06704v1","url_pdf":"https://arxiv.org/pdf/2210.06704v1.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":"collider-a-robust-training-framework-for","repo_url":"https://github.com/hmdolatabadi/collider","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2210.06704","atlas_url":"https://app.syntology.ai/?focus=2210.06704","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06704"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/hmdolatabadi/collider","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"ran_draft_wrong":2,"unverified":2},"by_repo_kind":{"official":{"samples":8,"ran":6,"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":"93a6f83b77333cee","entry":"accuracy","repo":"hmdolatabadi/collider","repo_kind":"official","path":"utils.py","file_url":"https://github.com/hmdolatabadi/collider/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"93a6f83b77333cee"}},{"code_sha256_prefix":"d9def42110729a85","entry":"conv1x1","repo":"hmdolatabadi/collider","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/hmdolatabadi/collider/blob/HEAD/models/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d9def42110729a85"}},{"code_sha256_prefix":"160bb14bd76201b4","entry":"conv3x3","repo":"hmdolatabadi/collider","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/hmdolatabadi/collider/blob/HEAD/models/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"160bb14bd76201b4"}},{"code_sha256_prefix":"3768614c02d02313","entry":"get_dataset","repo":"hmdolatabadi/collider","repo_kind":"official","path":"data_aux.py","file_url":"https://github.com/hmdolatabadi/collider/blob/HEAD/data_aux.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3768614c02d02313"}},{"code_sha256_prefix":"0bd6258603a6a95b","entry":"mle_batch","repo":"hmdolatabadi/collider","repo_kind":"official","path":"utils.py","file_url":"https://github.com/hmdolatabadi/collider/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0bd6258603a6a95b"}},{"code_sha256_prefix":"673b646b5aa019be","entry":"resnet32","repo":"hmdolatabadi/collider","repo_kind":"official","path":"models/resnet_cifar.py","file_url":"https://github.com/hmdolatabadi/collider/blob/HEAD/models/resnet_cifar.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"673b646b5aa019be"}},{"code_sha256_prefix":"23d880ed996f2ead","entry":"lazy_greedy_heap","repo":"hmdolatabadi/collider","repo_kind":"official","path":"lazyGreedy.py","file_url":"https://github.com/hmdolatabadi/collider/blob/HEAD/lazyGreedy.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":"23d880ed996f2ead"}},{"code_sha256_prefix":"f1efc5f21f78fc9d","entry":"resnet18","repo":"hmdolatabadi/collider","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/hmdolatabadi/collider/blob/HEAD/models/resnet.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":"f1efc5f21f78fc9d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}