{"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/why-should-adversarial-perturbations-be","title":"Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLP","arxiv_id":"2210.10683","date":"2022-10-19","proceeding":null,"authors":["Yangyi Chen","Hongcheng Gao","Ganqu Cui","Fanchao Qi","Longtao Huang","Zhiyuan Liu","Maosong Sun"],"abstract":"Textual adversarial samples play important roles in multiple subfields of NLP research, including security, evaluation, explainability, and data augmentation. However, most work mixes all these roles, obscuring the problem definitions and research goals of the security role that aims to reveal the practical concerns of NLP models. In this paper, we rethink the research paradigm of textual adversarial samples in security scenarios. We discuss the deficiencies in previous work and propose our suggestions that the research on the Security-oriented adversarial NLP (SoadNLP) should: (1) evaluate their methods on security tasks to demonstrate the real-world concerns; (2) consider real-world attackers' goals, instead of developing impractical methods. To this end, we first collect, process, and release a security datasets collection Advbench. Then, we reformalize the task and adjust the emphasis on different goals in SoadNLP. Next, we propose a simple method based on heuristic rules that can easily fulfill the actual adversarial goals to simulate real-world attack methods. We conduct experiments on both the attack and the defense sides on Advbench. Experimental results show that our method has higher practical value, indicating that the research paradigm in SoadNLP may start from our new benchmark. All the code and data of Advbench can be obtained at \\url{https://github.com/thunlp/Advbench}.","url_abs":"https://arxiv.org/abs/2210.10683v1","url_pdf":"https://arxiv.org/pdf/2210.10683v1.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":"why-should-adversarial-perturbations-be","repo_url":"https://github.com/thunlp/advbench","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"why-should-adversarial-perturbations-be","repo_url":"https://github.com/yang-yan-yang-yan/sop","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.10683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.10683"}},"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/yang-yan-yang-yan/sop","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thunlp/advbench","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/thunlp/Advbench","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"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":"5c709bda0e98881d","entry":"get_output_label","repo":"thunlp/Advbench","repo_kind":"official","path":"src/rocket.py","file_url":"https://github.com/thunlp/Advbench/blob/HEAD/src/rocket.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":"5c709bda0e98881d"}},{"code_sha256_prefix":"6c8ed858842dcafd","entry":"insert_irrelevant","repo":"thunlp/Advbench","repo_kind":"official","path":"src/attack_util.py","file_url":"https://github.com/thunlp/Advbench/blob/HEAD/src/attack_util.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":"6c8ed858842dcafd"}},{"code_sha256_prefix":"c86acd0c84b06bc6","entry":"insert_long_distractor","repo":"thunlp/Advbench","repo_kind":"official","path":"src/attack_util.py","file_url":"https://github.com/thunlp/Advbench/blob/HEAD/src/attack_util.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":"c86acd0c84b06bc6"}},{"code_sha256_prefix":"77003255936bef5e","entry":"insert_space","repo":"thunlp/Advbench","repo_kind":"official","path":"src/attack_util.py","file_url":"https://github.com/thunlp/Advbench/blob/HEAD/src/attack_util.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":"77003255936bef5e"}},{"code_sha256_prefix":"998751eb697aaee5","entry":"load_data","repo":"thunlp/Advbench","repo_kind":"official","path":"src/base_attack.py","file_url":"https://github.com/thunlp/Advbench/blob/HEAD/src/base_attack.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":"998751eb697aaee5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}