{"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/mixednuts-training-free-accuracy-robustness","title":"MixedNUTS: Training-Free Accuracy-Robustness Balance via Nonlinearly Mixed Classifiers","arxiv_id":"2402.02263","date":"2024-02-03","proceeding":null,"authors":["Yatong Bai","Mo Zhou","Vishal M. Patel","Somayeh Sojoudi"],"abstract":"Adversarial robustness often comes at the cost of degraded accuracy, impeding real-life applications of robust classification models. Training-based solutions for better trade-offs are limited by incompatibilities with already-trained high-performance large models, necessitating the exploration of training-free ensemble approaches. Observing that robust models are more confident in correct predictions than in incorrect ones on clean and adversarial data alike, we speculate amplifying this \"benign confidence property\" can reconcile accuracy and robustness in an ensemble setting. To achieve so, we propose \"MixedNUTS\", a training-free method where the output logits of a robust classifier and a standard non-robust classifier are processed by nonlinear transformations with only three parameters, which are optimized through an efficient algorithm. MixedNUTS then converts the transformed logits into probabilities and mixes them as the overall output. On CIFAR-10, CIFAR-100, and ImageNet datasets, experimental results with custom strong adaptive attacks demonstrate MixedNUTS's vastly improved accuracy and near-SOTA robustness -- it boosts CIFAR-100 clean accuracy by 7.86 points, sacrificing merely 0.87 points in robust accuracy.","url_abs":"https://arxiv.org/abs/2402.02263v5","url_pdf":"https://arxiv.org/pdf/2402.02263v5.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":"mixednuts-training-free-accuracy-robustness","repo_url":"https://github.com/Bai-YT/MixedNUTS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"adversarial-robustness","task_name":"Adversarial Robustness"},{"task_slug":"robust-classification","task_name":"Robust classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.02263","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.02263"}},"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/Bai-YT/MixedNUTS","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"ran":2,"ran_violates":1},"by_repo_kind":{"official":{"samples":5,"ran":5,"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":"ee80cf467065076b","entry":"conv1x1","repo":"Bai-YT/MixedNUTS","repo_kind":"official","path":"models/base_models/bit_rn.py","file_url":"https://github.com/Bai-YT/MixedNUTS/blob/HEAD/models/base_models/bit_rn.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":"ee80cf467065076b"}},{"code_sha256_prefix":"f01b8d3901f0b289","entry":"conv3x3","repo":"Bai-YT/MixedNUTS","repo_kind":"official","path":"models/base_models/bit_rn.py","file_url":"https://github.com/Bai-YT/MixedNUTS/blob/HEAD/models/base_models/bit_rn.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":"f01b8d3901f0b289"}},{"code_sha256_prefix":"b75085f804f343b9","entry":"load_sd_relaxed","repo":"Bai-YT/MixedNUTS","repo_kind":"official","path":"utils/model_utils.py","file_url":"https://github.com/Bai-YT/MixedNUTS/blob/HEAD/utils/model_utils.py","link_basis":"first_harvest_node","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":"b75085f804f343b9"}},{"code_sha256_prefix":"c185ad268410ac55","entry":"normalize_topk","repo":"Bai-YT/MixedNUTS","repo_kind":"official","path":"models/output_maps.py","file_url":"https://github.com/Bai-YT/MixedNUTS/blob/HEAD/models/output_maps.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c185ad268410ac55"}},{"code_sha256_prefix":"7023eb86801bb3a3","entry":"tf2th","repo":"Bai-YT/MixedNUTS","repo_kind":"official","path":"models/base_models/bit_rn.py","file_url":"https://github.com/Bai-YT/MixedNUTS/blob/HEAD/models/base_models/bit_rn.py","link_basis":"plan_row","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7023eb86801bb3a3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}