{"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/ead-elastic-net-attacks-to-deep-neural","title":"EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples","arxiv_id":"1709.04114","date":"2017-09-13","proceeding":null,"authors":["Pin-Yu Chen","Yash Sharma","huan zhang","Jin-Feng Yi","Cho-Jui Hsieh"],"abstract":"Recent studies have highlighted the vulnerability of deep neural networks\n(DNNs) to adversarial examples - a visually indistinguishable adversarial image\ncan easily be crafted to cause a well-trained model to misclassify. Existing\nmethods for crafting adversarial examples are based on $L_2$ and $L_\\infty$\ndistortion metrics. However, despite the fact that $L_1$ distortion accounts\nfor the total variation and encourages sparsity in the perturbation, little has\nbeen developed for crafting $L_1$-based adversarial examples. In this paper, we\nformulate the process of attacking DNNs via adversarial examples as an\nelastic-net regularized optimization problem. Our elastic-net attacks to DNNs\n(EAD) feature $L_1$-oriented adversarial examples and include the\nstate-of-the-art $L_2$ attack as a special case. Experimental results on MNIST,\nCIFAR10 and ImageNet show that EAD can yield a distinct set of adversarial\nexamples with small $L_1$ distortion and attains similar attack performance to\nthe state-of-the-art methods in different attack scenarios. More importantly,\nEAD leads to improved attack transferability and complements adversarial\ntraining for DNNs, suggesting novel insights on leveraging $L_1$ distortion in\nadversarial machine learning and security implications of DNNs.","url_abs":"http://arxiv.org/abs/1709.04114v3","url_pdf":"http://arxiv.org/pdf/1709.04114v3.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":"ead-elastic-net-attacks-to-deep-neural","repo_url":"https://github.com/ysharma1126/EAD-Attack","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"ead-elastic-net-attacks-to-deep-neural","repo_url":"https://github.com/IBM/EAD-Attack","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"ead-elastic-net-attacks-to-deep-neural","repo_url":"https://github.com/BorealisAI/advertorch/blob/master/advertorch/attacks/ead.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"ead-elastic-net-attacks-to-deep-neural","repo_url":"https://github.com/Trusted-AI/adversarial-robustness-toolbox/blob/main/art/attacks/evasion/elastic_net.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"ead-elastic-net-attacks-to-deep-neural","repo_url":"https://github.com/bethgelab/foolbox/blob/master/foolbox/attacks/ead.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":null},{"paper_slug":"ead-elastic-net-attacks-to-deep-neural","repo_url":"https://github.com/cleverhans-lab/cleverhans/blob/master/cleverhans_v3.1.0/cleverhans/attacks/elastic_net_method.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"adversarial-attack","task_name":"Adversarial Attack"},{"task_slug":"adversarial-robustness","task_name":"Adversarial Robustness"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1709.04114","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1709.04114"}},"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/BorealisAI/advertorch/blob/master/advertorch/attacks/ead.py","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cleverhans-lab/cleverhans/blob/master/cleverhans_v3.1.0/cleverhans/attacks/elastic_net_method.py","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Trusted-AI/adversarial-robustness-toolbox/blob/main/art/attacks/evasion/elastic_net.py","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/IBM/EAD-Attack","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ysharma1126/EAD-Attack","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bethgelab/foolbox/blob/master/foolbox/attacks/ead.py","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"listed":{"samples":1,"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":1,"samples":[{"code_sha256_prefix":"455253112a78ff1e","entry":"generate_data","repo":"IBM/EAD-Attack","repo_kind":"listed","path":"test_attack.py","file_url":"https://github.com/IBM/EAD-Attack/blob/HEAD/test_attack.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"455253112a78ff1e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}