{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/advcodec-towards-a-unified-framework-for-1","title":"T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted Attack","arxiv_id":"1912.10375","date":"2019-12-22","proceeding":"EMNLP 2020 11","authors":["Boxin Wang","Hengzhi Pei","Boyuan Pan","Qian Chen","Shuohang Wang","Bo Li"],"abstract":"Adversarial attacks against natural language processing systems, which perform seemingly innocuous modifications to inputs, can induce arbitrary mistakes to the target models. Though raised great concerns, such adversarial attacks can be leveraged to estimate the robustness of NLP models. Compared with the adversarial example generation in continuous data domain (e.g., image), generating adversarial text that preserves the original meaning is challenging since the text space is discrete and non-differentiable. To handle these challenges, we propose a target-controllable adversarial attack framework T3, which is applicable to a range of NLP tasks. In particular, we propose a tree-based autoencoder to embed the discrete text data into a continuous representation space, upon which we optimize the adversarial perturbation. A novel tree-based decoder is then applied to regularize the syntactic correctness of the generated text and manipulate it on either sentence (T3(Sent)) or word (T3(Word)) level. We consider two most representative NLP tasks: sentiment analysis and question answering (QA). Extensive experimental results and human studies show that T3 generated adversarial texts can successfully manipulate the NLP models to output the targeted incorrect answer without misleading the human. Moreover, we show that the generated adversarial texts have high transferability which enables the black-box attacks in practice. Our work sheds light on an effective and general way to examine the robustness of NLP models. Our code is publicly available at https://github.com/AI-secure/T3/.","url_abs":"https://arxiv.org/abs/1912.10375v2","url_pdf":"https://arxiv.org/pdf/1912.10375v2.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":"advcodec-towards-a-unified-framework-for-1","repo_url":"https://github.com/AI-secure/T3","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"advcodec-towards-a-unified-framework-for-1","repo_url":"https://github.com/aisecure/AdvCodec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"advcodec-towards-a-unified-framework-for-1","repo_url":"https://github.com/yangyi-chen/maya","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"adversarial-attack","task_name":"Adversarial Attack"},{"task_slug":"adversarial-text","task_name":"Adversarial Text"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1912.10375","atlas_url":"https://app.syntology.ai/?focus=1912.10375","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1912.10375"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1912.10375\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1912.10375"},"call":"get_concepts_for_paper(arxiv_id=\"1912.10375\")"}],"by_repo":[{"repo":"AI-secure/T3","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"aisecure/AdvCodec","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"yangyi-chen/maya","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"6fe212b6cabc6d4f5f94cf66ee02bf9697806f97ad44b1858fa028aea5184095","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}