{"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/certified-robustness-for-deep-equilibrium-1","title":"Certified Robustness for Deep Equilibrium Models via Serialized Random Smoothing","arxiv_id":"2411.00899","date":"2024-11-01","proceeding":null,"authors":["Weizhi Gao","Zhichao Hou","Han Xu","Xiaorui Liu"],"abstract":"Implicit models such as Deep Equilibrium Models (DEQs) have emerged as promising alternative approaches for building deep neural networks. Their certified robustness has gained increasing research attention due to security concerns. Existing certified defenses for DEQs employing deterministic certification methods such as interval bound propagation and Lipschitz-bounds can not certify on large-scale datasets. Besides, they are also restricted to specific forms of DEQs. In this paper, we provide the first randomized smoothing certified defense for DEQs to solve these limitations. Our study reveals that simply applying randomized smoothing to certify DEQs provides certified robustness generalized to large-scale datasets but incurs extremely expensive computation costs. To reduce computational redundancy, we propose a novel Serialized Randomized Smoothing (SRS) approach that leverages historical information. Additionally, we derive a new certified radius estimation for SRS to theoretically ensure the correctness of our algorithm. Extensive experiments and ablation studies on image recognition demonstrate that our algorithm can significantly accelerate the certification of DEQs by up to 7x almost without sacrificing the certified accuracy. Our code is available at https://github.com/WeizhiGao/Serialized-Randomized-Smoothing.","url_abs":"https://arxiv.org/abs/2411.00899v1","url_pdf":"https://arxiv.org/pdf/2411.00899v1.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":"certified-robustness-for-deep-equilibrium-1","repo_url":"https://github.com/weizhigao/serialized-randomized-smoothing","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"randomized-smoothing","method_name":"Randomized Smoothing"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.00899","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00899"}},"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":"deterministic:regex_extraction","url":"https://github.com/WeizhiGao/Serialized-Randomized-Smoothing","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/weizhigao/serialized-randomized-smoothing","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":5,"ran_honours":1,"unverified":8},"by_repo_kind":{"official":{"samples":14,"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":"fac5364e2f53c6db","entry":"conv3x3","repo":"WeizhiGao/Serialized-Randomized-Smoothing","repo_kind":"official","path":"SRS/code/archs/cifar_resnet.py","file_url":"https://github.com/WeizhiGao/Serialized-Randomized-Smoothing/blob/HEAD/SRS/code/archs/cifar_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":"fac5364e2f53c6db"}},{"code_sha256_prefix":"bc359191fdd6e179","entry":"conv3x3","repo":"WeizhiGao/Serialized-Randomized-Smoothing","repo_kind":"official","path":"DEQ/lib/layer_utils.py","file_url":"https://github.com/WeizhiGao/Serialized-Randomized-Smoothing/blob/HEAD/DEQ/lib/layer_utils.py","link_basis":"plan_row","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":"bc359191fdd6e179"}},{"code_sha256_prefix":"cf5710371bcfb0ab","entry":"line_search","repo":"WeizhiGao/Serialized-Randomized-Smoothing","repo_kind":"official","path":"DEQ/lib/solvers.py","file_url":"https://github.com/WeizhiGao/Serialized-Randomized-Smoothing/blob/HEAD/DEQ/lib/solvers.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cf5710371bcfb0ab"}},{"code_sha256_prefix":"3c120cc50bc8c55f","entry":"power_method","repo":"WeizhiGao/Serialized-Randomized-Smoothing","repo_kind":"official","path":"DEQ/lib/jacobian.py","file_url":"https://github.com/WeizhiGao/Serialized-Randomized-Smoothing/blob/HEAD/DEQ/lib/jacobian.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3c120cc50bc8c55f"}},{"code_sha256_prefix":"968a8f446ad3c5b1","entry":"rmatvec","repo":"WeizhiGao/Serialized-Randomized-Smoothing","repo_kind":"official","path":"DEQ/lib/solvers.py","file_url":"https://github.com/WeizhiGao/Serialized-Randomized-Smoothing/blob/HEAD/DEQ/lib/solvers.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"968a8f446ad3c5b1"}},{"code_sha256_prefix":"b2b5022f654ee4d3","entry":"scalar_search_armijo","repo":"WeizhiGao/Serialized-Randomized-Smoothing","repo_kind":"official","path":"DEQ/lib/solvers.py","file_url":"https://github.com/WeizhiGao/Serialized-Randomized-Smoothing/blob/HEAD/DEQ/lib/solvers.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b2b5022f654ee4d3"}},{"code_sha256_prefix":"df1c4e8a21c5f2ef","entry":"embedded_dropout","repo":"WeizhiGao/Serialized-Randomized-Smoothing","repo_kind":"official","path":"DEQ/lib/optimizations.py","file_url":"https://github.com/WeizhiGao/Serialized-Randomized-Smoothing/blob/HEAD/DEQ/lib/optimizations.py","link_basis":"plan_row","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":"df1c4e8a21c5f2ef"}},{"code_sha256_prefix":"667ac97f3d05bca6","entry":"get_dataset","repo":"WeizhiGao/Serialized-Randomized-Smoothing","repo_kind":"official","path":"SRS/code/datasets.py","file_url":"https://github.com/WeizhiGao/Serialized-Randomized-Smoothing/blob/HEAD/SRS/code/datasets.py","link_basis":"first_harvest_node","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":"667ac97f3d05bca6"}},{"code_sha256_prefix":"8c99213918181c27","entry":"get_num_classes","repo":"WeizhiGao/Serialized-Randomized-Smoothing","repo_kind":"official","path":"SRS/code/datasets.py","file_url":"https://github.com/WeizhiGao/Serialized-Randomized-Smoothing/blob/HEAD/SRS/code/datasets.py","link_basis":"first_harvest_node","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":"8c99213918181c27"}},{"code_sha256_prefix":"3d07af47a6ba65bd","entry":"jac_loss_estimate","repo":"WeizhiGao/Serialized-Randomized-Smoothing","repo_kind":"official","path":"DEQ/lib/jacobian.py","file_url":"https://github.com/WeizhiGao/Serialized-Randomized-Smoothing/blob/HEAD/DEQ/lib/jacobian.py","link_basis":"plan_row","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":"3d07af47a6ba65bd"}},{"code_sha256_prefix":"e193f0d97cdfd598","entry":"list2vec","repo":"WeizhiGao/Serialized-Randomized-Smoothing","repo_kind":"official","path":"DEQ/lib/layer_utils.py","file_url":"https://github.com/WeizhiGao/Serialized-Randomized-Smoothing/blob/HEAD/DEQ/lib/layer_utils.py","link_basis":"plan_row","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":"e193f0d97cdfd598"}},{"code_sha256_prefix":"f06524d1a24b825a","entry":"matrix_diag","repo":"WeizhiGao/Serialized-Randomized-Smoothing","repo_kind":"official","path":"DEQ/lib/optimizations.py","file_url":"https://github.com/WeizhiGao/Serialized-Randomized-Smoothing/blob/HEAD/DEQ/lib/optimizations.py","link_basis":"plan_row","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":"f06524d1a24b825a"}},{"code_sha256_prefix":"bfc68a2da5929c5b","entry":"vec2list","repo":"WeizhiGao/Serialized-Randomized-Smoothing","repo_kind":"official","path":"DEQ/lib/layer_utils.py","file_url":"https://github.com/WeizhiGao/Serialized-Randomized-Smoothing/blob/HEAD/DEQ/lib/layer_utils.py","link_basis":"plan_row","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":"bfc68a2da5929c5b"}},{"code_sha256_prefix":"4bf00e788db9f349","entry":"weight_norm","repo":"WeizhiGao/Serialized-Randomized-Smoothing","repo_kind":"official","path":"DEQ/lib/optimizations.py","file_url":"https://github.com/WeizhiGao/Serialized-Randomized-Smoothing/blob/HEAD/DEQ/lib/optimizations.py","link_basis":"plan_row","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":"4bf00e788db9f349"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}