{"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/introducing-competition-to-boost-the-1","title":"Introducing Competition to Boost the Transferability of Targeted Adversarial Examples through Clean Feature Mixup","arxiv_id":"2305.14846","date":"2023-05-24","proceeding":"CVPR 2023 1","authors":["Junyoung Byun","Myung-Joon Kwon","Seungju Cho","Yoonji Kim","Changick Kim"],"abstract":"Deep neural networks are widely known to be susceptible to adversarial examples, which can cause incorrect predictions through subtle input modifications. These adversarial examples tend to be transferable between models, but targeted attacks still have lower attack success rates due to significant variations in decision boundaries. To enhance the transferability of targeted adversarial examples, we propose introducing competition into the optimization process. Our idea is to craft adversarial perturbations in the presence of two new types of competitor noises: adversarial perturbations towards different target classes and friendly perturbations towards the correct class. With these competitors, even if an adversarial example deceives a network to extract specific features leading to the target class, this disturbance can be suppressed by other competitors. Therefore, within this competition, adversarial examples should take different attack strategies by leveraging more diverse features to overwhelm their interference, leading to improving their transferability to different models. Considering the computational complexity, we efficiently simulate various interference from these two types of competitors in feature space by randomly mixing up stored clean features in the model inference and named this method Clean Feature Mixup (CFM). Our extensive experimental results on the ImageNet-Compatible and CIFAR-10 datasets show that the proposed method outperforms the existing baselines with a clear margin. Our code is available at https://github.com/dreamflake/CFM.","url_abs":"https://arxiv.org/abs/2305.14846v1","url_pdf":"https://arxiv.org/pdf/2305.14846v1.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":"introducing-competition-to-boost-the-1","repo_url":"https://github.com/dreamflake/cfm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"mixup","method_name":"Mixup"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.14846","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14846"}},"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/dreamflake/cfm","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/dreamflake/CFM","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":4,"ran_violates":1,"unverified":5},"by_repo_kind":{"official":{"samples":10,"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":"ccdb43ecb62325f2","entry":"Linf_PGD","repo":"dreamflake/cfm","repo_kind":"official","path":"DVERGE/distillation.py","file_url":"https://github.com/dreamflake/cfm/blob/HEAD/DVERGE/distillation.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":"ccdb43ecb62325f2"}},{"code_sha256_prefix":"c5ea22297f8dcf56","entry":"gradient_wrt_feature","repo":"dreamflake/cfm","repo_kind":"official","path":"DVERGE/distillation.py","file_url":"https://github.com/dreamflake/cfm/blob/HEAD/DVERGE/distillation.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":"c5ea22297f8dcf56"}},{"code_sha256_prefix":"a7432682e97da06b","entry":"gradient_wrt_input","repo":"dreamflake/cfm","repo_kind":"official","path":"DVERGE/distillation.py","file_url":"https://github.com/dreamflake/cfm/blob/HEAD/DVERGE/distillation.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":"a7432682e97da06b"}},{"code_sha256_prefix":"9e4f4d7edbf00ba0","entry":"load_ground_truth","repo":"dreamflake/cfm","repo_kind":"official","path":"eval_attacks.py","file_url":"https://github.com/dreamflake/cfm/blob/HEAD/eval_attacks.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":"9e4f4d7edbf00ba0"}},{"code_sha256_prefix":"8605dc8a088f3db8","entry":"str2bool","repo":"dreamflake/cfm","repo_kind":"official","path":"utils.py","file_url":"https://github.com/dreamflake/cfm/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8605dc8a088f3db8"}},{"code_sha256_prefix":"8916ca54576c0afd","entry":"FeatureMixup","repo":"dreamflake/CFM","repo_kind":"official","path":"attacks.py","file_url":"https://github.com/dreamflake/CFM/blob/HEAD/attacks.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":"8916ca54576c0afd"}},{"code_sha256_prefix":"50956689e2a717ad","entry":"compute_rotation","repo":"dreamflake/cfm","repo_kind":"official","path":"attacks.py","file_url":"https://github.com/dreamflake/cfm/blob/HEAD/attacks.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":"50956689e2a717ad"}},{"code_sha256_prefix":"ae3730ed44c5ff5b","entry":"load_ground_truth_cifar10","repo":"dreamflake/cfm","repo_kind":"official","path":"eval_attacks.py","file_url":"https://github.com/dreamflake/cfm/blob/HEAD/eval_attacks.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":"ae3730ed44c5ff5b"}},{"code_sha256_prefix":"c1e41af537b4027c","entry":"model_dataset_from_store","repo":"dreamflake/cfm","repo_kind":"official","path":"MadryLab/model_utils.py","file_url":"https://github.com/dreamflake/cfm/blob/HEAD/MadryLab/model_utils.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":"c1e41af537b4027c"}},{"code_sha256_prefix":"422be6728d89fc79","entry":"rigid_transform","repo":"dreamflake/cfm","repo_kind":"official","path":"attacks.py","file_url":"https://github.com/dreamflake/cfm/blob/HEAD/attacks.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":"422be6728d89fc79"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}