{"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/text-processing-like-humans-do-visually","title":"Text Processing Like Humans Do: Visually Attacking and Shielding NLP Systems","arxiv_id":"1903.11508","date":"2019-03-27","proceeding":"NAACL 2019 6","authors":["Steffen Eger","Gözde Gül Şahin","Andreas Rücklé","Ji-Ung Lee","Claudia Schulz","Mohsen Mesgar","Krishnkant Swarnkar","Edwin Simpson","Iryna Gurevych"],"abstract":"Visual modifications to text are often used to obfuscate offensive comments in social media (e.g., \"!d10t\") or as a writing style (\"1337\" in \"leet speak\"), among other scenarios. We consider this as a new type of adversarial attack in NLP, a setting to which humans are very robust, as our experiments with both simple and more difficult visual input perturbations demonstrate. We then investigate the impact of visual adversarial attacks on current NLP systems on character-, word-, and sentence-level tasks, showing that both neural and non-neural models are, in contrast to humans, extremely sensitive to such attacks, suffering performance decreases of up to 82\\%. We then explore three shielding methods---visual character embeddings, adversarial training, and rule-based recovery---which substantially improve the robustness of the models. However, the shielding methods still fall behind performances achieved in non-attack scenarios, which demonstrates the difficulty of dealing with visual attacks.","url_abs":"https://arxiv.org/abs/1903.11508v2","url_pdf":"https://arxiv.org/pdf/1903.11508v2.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":"text-processing-like-humans-do-visually","repo_url":"https://github.com/UKPLab/naacl2019-like-humans-visual-attacks","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"adversarial-attack","task_name":"Adversarial Attack"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.11508","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.11508"}},"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/UKPLab/naacl2019-like-humans-visual-attacks","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":1},"by_repo_kind":{"official":{"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":0,"samples":[{"code_sha256_prefix":"2ac5df460339e261","entry":"getInitializer","repo":"UKPLab/naacl2019-like-humans-visual-attacks","repo_kind":"official","path":"code/G2P/handleHyper.py","file_url":"https://github.com/UKPLab/naacl2019-like-humans-visual-attacks/blob/HEAD/code/G2P/handleHyper.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2ac5df460339e261"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}