{"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/genattack-practical-black-box-attacks-with","title":"GenAttack: Practical Black-box Attacks with Gradient-Free Optimization","arxiv_id":"1805.11090","date":"2018-05-28","proceeding":null,"authors":["Moustafa Alzantot","Yash Sharma","Supriyo Chakraborty","huan zhang","Cho-Jui Hsieh","Mani Srivastava"],"abstract":"Deep neural networks are vulnerable to adversarial examples, even in the black-box setting, where the attacker is restricted solely to query access. Existing black-box approaches to generating adversarial examples typically require a significant number of queries, either for training a substitute network or performing gradient estimation. We introduce GenAttack, a gradient-free optimization technique that uses genetic algorithms for synthesizing adversarial examples in the black-box setting. Our experiments on different datasets (MNIST, CIFAR-10, and ImageNet) show that GenAttack can successfully generate visually imperceptible adversarial examples against state-of-the-art image recognition models with orders of magnitude fewer queries than previous approaches. Against MNIST and CIFAR-10 models, GenAttack required roughly 2,126 and 2,568 times fewer queries respectively, than ZOO, the prior state-of-the-art black-box attack. In order to scale up the attack to large-scale high-dimensional ImageNet models, we perform a series of optimizations that further improve the query efficiency of our attack leading to 237 times fewer queries against the Inception-v3 model than ZOO. Furthermore, we show that GenAttack can successfully attack some state-of-the-art ImageNet defenses, including ensemble adversarial training and non-differentiable or randomized input transformations. Our results suggest that evolutionary algorithms open up a promising area of research into effective black-box attacks.","url_abs":"https://arxiv.org/abs/1805.11090v3","url_pdf":"https://arxiv.org/pdf/1805.11090v3.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":"genattack-practical-black-box-attacks-with","repo_url":"https://github.com/nesl/adversarial_genattack","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"genattack-practical-black-box-attacks-with","repo_url":"https://github.com/maremun/GenAttackMCS2018","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"genattack-practical-black-box-attacks-with","repo_url":"https://github.com/bethgelab/foolbox/blob/master/foolbox/attacks/gen_attack.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":null}],"tasks":[{"task_slug":"adversarial-attack","task_name":"Adversarial Attack"},{"task_slug":"adversarial-robustness","task_name":"Adversarial Robustness"},{"task_slug":"evolutionary-algorithms","task_name":"Evolutionary Algorithms"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"auxiliary-classifier","method_name":"Auxiliary Classifier"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"inception-v3","method_name":"Inception-v3"},{"method_slug":"inception-v3-module","method_name":"Inception-v3 Module"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"rmsprop","method_name":"RMSProp"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.11090","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.11090"}},"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/bethgelab/foolbox/blob/master/foolbox/attacks/gen_attack.py","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nesl/adversarial_genattack","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/maremun/GenAttackMCS2018","reach":null}],"summary":{"ran_honours":2,"unverified":10},"by_repo_kind":{"official":{"samples":9,"ran":2,"repositories":1},"listed":{"samples":3,"ran":0,"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":"86c9fa246614e9a9","entry":"extract_data","repo":"nesl/adversarial_genattack","repo_kind":"official","path":"setup_mnist.py","file_url":"https://github.com/nesl/adversarial_genattack/blob/HEAD/setup_mnist.py","link_basis":"harvester_set","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":"86c9fa246614e9a9"}},{"code_sha256_prefix":"a0cf6bb81ff7819e","entry":"extract_labels","repo":"nesl/adversarial_genattack","repo_kind":"official","path":"setup_mnist.py","file_url":"https://github.com/nesl/adversarial_genattack/blob/HEAD/setup_mnist.py","link_basis":"harvester_set","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":"a0cf6bb81ff7819e"}},{"code_sha256_prefix":"d0d8c5d6a3a88cd8","entry":"crossover","repo":"maremun/GenAttackMCS2018","repo_kind":"listed","path":"genattack.py","file_url":"https://github.com/maremun/GenAttackMCS2018/blob/HEAD/genattack.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":"d0d8c5d6a3a88cd8"}},{"code_sha256_prefix":"bb5e83c39bdec690","entry":"generate_data","repo":"nesl/adversarial_genattack","repo_kind":"official","path":"utils.py","file_url":"https://github.com/nesl/adversarial_genattack/blob/HEAD/utils.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":"bb5e83c39bdec690"}},{"code_sha256_prefix":"ec5f90b9679633c5","entry":"get_mutation","repo":"maremun/GenAttackMCS2018","repo_kind":"listed","path":"genattack.py","file_url":"https://github.com/maremun/GenAttackMCS2018/blob/HEAD/genattack.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":"ec5f90b9679633c5"}},{"code_sha256_prefix":"32ecbd87f915e308","entry":"l_2_dist","repo":"nesl/adversarial_genattack","repo_kind":"official","path":"utils.py","file_url":"https://github.com/nesl/adversarial_genattack/blob/HEAD/utils.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":"32ecbd87f915e308"}},{"code_sha256_prefix":"6f056b1dd2976681","entry":"l_inf_dist","repo":"nesl/adversarial_genattack","repo_kind":"official","path":"utils.py","file_url":"https://github.com/nesl/adversarial_genattack/blob/HEAD/utils.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":"6f056b1dd2976681"}},{"code_sha256_prefix":"ab7faf0047f2c872","entry":"load_batch","repo":"nesl/adversarial_genattack","repo_kind":"official","path":"setup_cifar.py","file_url":"https://github.com/nesl/adversarial_genattack/blob/HEAD/setup_cifar.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":"ab7faf0047f2c872"}},{"code_sha256_prefix":"3b4fb87c66244ebf","entry":"load_batch","repo":"nesl/adversarial_genattack","repo_kind":"official","path":"setup_cifar.py","file_url":"https://github.com/nesl/adversarial_genattack/blob/HEAD/setup_cifar.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":"3b4fb87c66244ebf"}},{"code_sha256_prefix":"59c8c9a8f20e44a9","entry":"readimg","repo":"nesl/adversarial_genattack","repo_kind":"official","path":"setup_inception.py","file_url":"https://github.com/nesl/adversarial_genattack/blob/HEAD/setup_inception.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":"59c8c9a8f20e44a9"}},{"code_sha256_prefix":"8b389eb9f5726984","entry":"train","repo":"nesl/adversarial_genattack","repo_kind":"official","path":"train_models.py","file_url":"https://github.com/nesl/adversarial_genattack/blob/HEAD/train_models.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":"8b389eb9f5726984"}},{"code_sha256_prefix":"23e2e9ee651bbb83","entry":"where","repo":"maremun/GenAttackMCS2018","repo_kind":"listed","path":"genattack.py","file_url":"https://github.com/maremun/GenAttackMCS2018/blob/HEAD/genattack.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":"23e2e9ee651bbb83"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}