{"id":"https://openalex.org/W4414856452","doi":"https://doi.org/10.1109/tnnls.2025.3609842","title":"Syntax-Oriented Shortcut: A Syntax Level Perturbing Algorithm for Preventing Text Data From Being Learned","display_name":"Syntax-Oriented Shortcut: A Syntax Level Perturbing Algorithm for Preventing Text Data From Being Learned","publication_year":2025,"publication_date":"2025-10-06","ids":{"openalex":"https://openalex.org/W4414856452","doi":"https://doi.org/10.1109/tnnls.2025.3609842","pmid":"https://pubmed.ncbi.nlm.nih.gov/41052174"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2025.3609842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3609842","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011750314","display_name":"Bo Li","orcid":"https://orcid.org/0000-0002-0241-4931"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Li","raw_affiliation_strings":["School of Artificial Intelligence, Anhui University, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0002-0241-4931","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Anhui University, Hefei, Anhui, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342310","display_name":"Kun Zhang","orcid":"https://orcid.org/0000-0002-0743-9003"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Zhang","raw_affiliation_strings":["School of Computer Science and Information Engineering and the Intelligent Interconnected Systems Laboratory of Anhui Province, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-0743-9003","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering and the Intelligent Interconnected Systems Laboratory of Anhui Province, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329996","display_name":"Xi Chen","orcid":"https://orcid.org/0000-0002-8911-4172"},"institutions":[{"id":"https://openalex.org/I4210137491","display_name":"National Science Centre","ror":"https://ror.org/03ha2q922","country_code":"PL","type":"government","lineage":["https://openalex.org/I4210137491"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Xi Chen","raw_affiliation_strings":["Hefei Comprehensive National Science Center, Institute of Dataspace, Hefei, Anhui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei Comprehensive National Science Center, Institute of Dataspace, Hefei, Anhui, China","institution_ids":["https://openalex.org/I4210137491"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051332325","display_name":"Richang Hong","orcid":"https://orcid.org/0000-0001-5461-3986"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Richang Hong","raw_affiliation_strings":["School of Computer and Information, Hefei University of Technology, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0001-5461-3986","affiliations":[{"raw_affiliation_string":"School of Computer and Information, Hefei University of Technology, Hefei, Anhui, China","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1027106,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"37","issue":"2","first_page":"632","last_page":"645"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.9402999877929688,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.9402999877929688,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.881600022315979},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.7289000153541565},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.7102000117301941},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5217000246047974},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4796999990940094},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.478300005197525},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.4611000120639801},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42570000886917114}],"concepts":[{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.881600022315979},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.794700026512146},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.7289000153541565},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.7102000117301941},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5217000246047974},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4814999997615814},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4796999990940094},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.478300005197525},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.4611000120639801},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4462999999523163},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42570000886917114},{"id":"https://openalex.org/C114408938","wikidata":"https://www.wikidata.org/wiki/Q333373","display_name":"Abstract syntax","level":3,"score":0.37529999017715454},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37459999322891235},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3531000018119812},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3521000146865845},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.3375999927520752},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3158999979496002},{"id":"https://openalex.org/C59415355","wikidata":"https://www.wikidata.org/wiki/Q3484781","display_name":"Text simplification","level":3,"score":0.30640000104904175},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.2962999939918518},{"id":"https://openalex.org/C58646249","wikidata":"https://www.wikidata.org/wiki/Q127380","display_name":"Abstract syntax tree","level":3,"score":0.2587999999523163}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2025.3609842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3609842","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:41052174","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41052174","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1376964976","display_name":null,"funder_award_id":"JZ2025HGTG0289","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2856465700","display_name":null,"funder_award_id":"PA2025IISL0114","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G6921662984","display_name":null,"funder_award_id":"62376086","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1493526108","https://openalex.org/W2123442489","https://openalex.org/W2130158090","https://openalex.org/W2788496822","https://openalex.org/W2883386984","https://openalex.org/W2931212643","https://openalex.org/W2950784811","https://openalex.org/W2965373594","https://openalex.org/W2997200074","https://openalex.org/W3040809437","https://openalex.org/W3154155772","https://openalex.org/W3156309620","https://openalex.org/W3211466672","https://openalex.org/W3213758632","https://openalex.org/W4225531949","https://openalex.org/W4285211815","https://openalex.org/W4285605523","https://openalex.org/W4286865884","https://openalex.org/W4287888417","https://openalex.org/W4380875839","https://openalex.org/W4382202528","https://openalex.org/W4385572007","https://openalex.org/W4385734201","https://openalex.org/W4385757404","https://openalex.org/W4400830279","https://openalex.org/W4403758929","https://openalex.org/W4404293797","https://openalex.org/W4407360741","https://openalex.org/W4412888959","https://openalex.org/W4416310693"],"related_works":[],"abstract_inverted_index":{"The":[0],"vast":[1],"availability":[2],"of":[3,12,21,34,84,128,226],"free":[4],"data":[5,40,55],"has":[6],"been":[7,28],"critical":[8],"to":[9,76,90,138,161,171,185,198,234],"the":[10,18,31,63,77,125,140,163,167,175,187,190,194,222,237],"success":[11],"large":[13],"language":[14,210,217],"models":[15,58,181,211],"(LLMs).":[16],"With":[17],"widespread":[19],"use":[20,33,43],"LLMs,":[22],"more":[23,25],"and":[24,67,81,193,224,236],"concerns":[26],"have":[27,48],"raised":[29],"about":[30],"unauthorized":[32,42],"publicly":[35,240],"available":[36,241],"data.":[37],"To":[38,103],"protect":[39],"from":[41,71,174],"for":[44,144],"training":[45],"models,":[46],"researchers":[47],"proposed":[49,228],"adding":[50],"imperceptible":[51,151],"perturbations":[52],"into":[53],"image":[54],"so":[56,196],"that":[57],"would":[59],"be":[60,183],"misled":[61,184],"by":[62,123],"generated":[64],"shortcut":[65,99,121,188],"features":[66,100],"cannot":[68],"mine":[69],"information":[70],"these":[72,88],"images.":[73],"However,":[74],"due":[75],"inherent":[78],"discrete":[79],"property":[80],"semantic":[82,94],"complexity":[83],"texts,":[85],"directly":[86],"applying":[87],"methods":[89],"text":[91,115,156,200],"will":[92,149,182],"cause":[93],"changes,":[95],"resulting":[96],"in":[97,107],"meaningless":[98],"being":[101],"constructed.":[102],"tackle":[104],"this":[105,108,179],"problem,":[106],"article,":[109],"we":[110,131],"design":[111],"a":[112,133,145,154],"novel":[113],"Unlearnable":[114],"examples":[116,201],"generation":[117],"algorithm":[118],"via":[119],"syntax-oriented":[120],"(UTE-SS)":[122],"incorporating":[124],"syntactic":[126],"structure":[127],"texts.":[129,177],"Specifically,":[130],"propose":[132],"syntax":[134,143,169,191],"template":[135,170,192],"generator":[136,157],"(STG)":[137],"generate":[139],"optimal":[141],"perturbing":[142,155],"given":[146],"category,":[147,195],"which":[148],"realize":[150],"perturbations.":[152],"Then,":[153],"(PTG)":[158],"is":[159,232,239],"designed":[160],"perturb":[162],"in-class":[164],"texts":[165],"with":[166],"selected":[168],"stably":[172],"deviate":[173],"original":[176],"Along":[178],"line,":[180],"learn":[186],"between":[189],"as":[197],"keep":[199],"unlearnable.":[202],"Extensive":[203],"experiments":[204],"over":[205],"eight":[206],"advanced":[207],"Transformer-based":[208],"pretrained":[209],"(PLMs)":[212],"on":[213],"four":[214],"different":[215],"natural":[216],"processing":[218],"(NLP)":[219],"tasks":[220],"demonstrate":[221],"effectiveness":[223],"flexibility":[225],"our":[227],"algorithm.":[229],"Our":[230],"method":[231],"easy":[233],"implement,":[235],"code":[238],"at":[242],"https://github.com/libolb/UTE-SS.":[243]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}