{"id":"https://openalex.org/W7203663718","doi":"https://doi.org/10.21203/rs.3.rs-10418588/v1","title":"AST-Level Semantic Watermarking Framework for AI-Generated Code: Robust Provenance Attribution via Structural Invariants","display_name":"AST-Level Semantic Watermarking Framework for AI-Generated Code: Robust Provenance Attribution via Structural Invariants","publication_year":2026,"publication_date":"2026-08-18","ids":{"openalex":"https://openalex.org/W7203663718","doi":"https://doi.org/10.21203/rs.3.rs-10418588/v1"},"language":"en","primary_location":{"id":"doi:10.21203/rs.3.rs-10418588/v1","doi":"https://doi.org/10.21203/rs.3.rs-10418588/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-10418588/v1","pdf_url":"https://www.researchsquare.com/article/rs-10418588/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.researchsquare.com/article/rs-10418588/latest.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140667050","display_name":"Alamin Abubakar Nataala","orcid":"https://orcid.org/0009-0001-9833-0846","observed_orcids":["https://orcid.org/0009-0001-9833-0846"]},"institutions":[{"id":"https://openalex.org/I902764099","display_name":"SEGi University","ror":"https://ror.org/05crr5s63","country_code":"MY","type":"education","lineage":["https://openalex.org/I902764099"]}],"countries":["MY"],"is_corresponding":true,"raw_author_name":"Alamin Abubakar Nataala","raw_affiliation_strings":["SEGi University College Kota Damansara: SEGi University Kota Damansara"],"raw_orcid":"https://orcid.org/0009-0001-9833-0846","affiliations":[{"raw_affiliation_string":"SEGi University College Kota Damansara: SEGi University Kota Damansara","institution_ids":["https://openalex.org/I902764099"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5140667050"],"corresponding_institution_ids":["https://openalex.org/I902764099"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.47269999980926514,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10260","display_name":"Software Engineering Research","score":0.47269999980926514,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10388","display_name":"Advanced Steganography and Watermarking Techniques","score":0.32839998602867126,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12122","display_name":"Physical Unclonable Functions (PUFs) and Hardware Security","score":0.1193000003695488,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/ai-generated-code","display_name":"AI-generated code","score":0.8309999704360962},{"id":"https://openalex.org/keywords/abstract-syntax-tree","display_name":"abstract syntax tree","score":0.8230000138282776},{"id":"https://openalex.org/keywords/provenance-attribution","display_name":"provenance attribution","score":0.718999981880188},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6449999809265137},{"id":"https://openalex.org/keywords/code-generation","display_name":"code generation","score":0.43700000643730164},{"id":"https://openalex.org/keywords/intellectual-property-protection","display_name":"intellectual property protection","score":0.6290000081062317},{"id":"https://openalex.org/keywords/structural-invariants","display_name":"structural invariants","score":0.6600000262260437},{"id":"https://openalex.org/keywords/variable-renaming","display_name":"variable renaming","score":0.4950000047683716},{"id":"https://openalex.org/keywords/code-formatting","display_name":"code formatting","score":0.6679999828338623},{"id":"https://openalex.org/keywords/cryptographic-signatures","display_name":"cryptographic signatures","score":0.6430000066757202}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7347000241279602},{"id":"https://openalex.org/C150817343","wikidata":"https://www.wikidata.org/wiki/Q875932","display_name":"Digital watermarking","level":3,"score":0.5065000057220459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4239000082015991},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40860000252723694},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.40689998865127563},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.40450000762939453},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3928000032901764},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.3774000108242035},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3750999867916107},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3723999857902527},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.36230000853538513},{"id":"https://openalex.org/C2777561058","wikidata":"https://www.wikidata.org/wiki/Q2652119","display_name":"Program comprehension","level":4,"score":0.35989999771118164},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.3441999852657318},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3287999927997589},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C111065885","wikidata":"https://www.wikidata.org/wiki/Q1189053","display_name":"Fuzz testing","level":3,"score":0.30300000309944153},{"id":"https://openalex.org/C145644426","wikidata":"https://www.wikidata.org/wiki/Q169411","display_name":"Unified Modeling Language","level":3,"score":0.30219998955726624},{"id":"https://openalex.org/C160191386","wikidata":"https://www.wikidata.org/wiki/Q868299","display_name":"Control flow","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C2780907237","wikidata":"https://www.wikidata.org/wiki/Q2986238","display_name":"Plagiarism detection","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C114408938","wikidata":"https://www.wikidata.org/wiki/Q333373","display_name":"Abstract syntax","level":3,"score":0.28439998626708984},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.2840999960899353},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C3073032","wikidata":"https://www.wikidata.org/wiki/Q15912075","display_name":"Information hiding","level":3,"score":0.27970001101493835},{"id":"https://openalex.org/C128942645","wikidata":"https://www.wikidata.org/wiki/Q1568346","display_name":"Test case","level":3,"score":0.27900001406669617},{"id":"https://openalex.org/C55526617","wikidata":"https://www.wikidata.org/wiki/Q719375","display_name":"Operand","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26570001244544983},{"id":"https://openalex.org/C137287247","wikidata":"https://www.wikidata.org/wiki/Q1329550","display_name":"Static program analysis","level":4,"score":0.26420000195503235},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C50637493","wikidata":"https://www.wikidata.org/wiki/Q1136781","display_name":"Morphing","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C97686452","wikidata":"https://www.wikidata.org/wiki/Q7604153","display_name":"Static analysis","level":2,"score":0.2563000023365021}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21203/rs.3.rs-10418588/v1","doi":"https://doi.org/10.21203/rs.3.rs-10418588/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-10418588/v1","pdf_url":"https://www.researchsquare.com/article/rs-10418588/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.21203/rs.3.rs-10418588/v1","doi":"https://doi.org/10.21203/rs.3.rs-10418588/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-10418588/v1","pdf_url":"https://www.researchsquare.com/article/rs-10418588/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203663718.pdf","grobid_xml":"https://content.openalex.org/works/W7203663718.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4417102376"],"related_works":["https://openalex.org/W4393299607","https://openalex.org/W7213771854","https://openalex.org/W7215107144","https://openalex.org/W4391799121","https://openalex.org/W7140106568","https://openalex.org/W7162296932","https://openalex.org/W7168251062","https://openalex.org/W4404782027","https://openalex.org/W7116210404","https://openalex.org/W4407185626"],"abstract_inverted_index":{"Abstract":[0,93],"The":[1],"rapid":[2],"proliferation":[3],"of":[4,97,107,133],"Large":[5],"Language":[6],"Models":[7],"(LLMs)":[8],"specialized":[9],"in":[10],"automated":[11,72],"code":[12,36,192,225],"generation":[13],"has":[14],"revolutionized":[15],"software":[16,31,64],"engineering":[17],"while":[18,203],"simultaneously":[19],"introducing":[20],"severe":[21],"vulnerabilities":[22],"concerning":[23],"intellectual":[24],"property":[25],"(IP)":[26],"theft,":[27],"academic":[28],"dishonesty,":[29],"and":[30,54,67,76,118,187,199],"supply":[32],"chain":[33],"integrity.":[34],"Existing":[35],"watermarking":[37,86],"techniques":[38],"predominantly":[39],"operate":[40],"during":[41],"inference-time":[42],"autoregressive":[43],"decoding,":[44],"biasing":[45],"token":[46],"selection":[47],"via":[48,147],"logits":[49],"manipulation.":[50],"However,":[51],"these":[52],"text-level":[53],"entropy-based":[55,200],"watermarks":[56],"exhibit":[57],"catastrophic":[58],"fragility":[59],"when":[60],"exposed":[61],"to":[62],"standard":[63,165],"maintenance":[65],"workflows":[66],"semantic-preserving":[68],"transformations,":[69],"such":[70],"as":[71],"formatting,":[73],"variable":[74,185],"renaming,":[75,186],"dead-code":[77],"injection.":[78],"This":[79,212],"paper":[80],"proposes":[81],"a":[82,148,154,158,205,215],"novel,":[83],"post-hoc,":[84],"structure-aware":[85],"framework":[87,124,171],"that":[88,168],"operates":[89],"directly":[90],"upon":[91],"the":[92,98,122,130,134,169],"Syntax":[94],"Tree":[95],"(AST)":[96],"generated":[99],"source":[100],"code.":[101],"By":[102],"formalizing":[103],"an":[104],"invariant":[105],"dictionary":[106],"deterministic,":[108],"semantics-preserving":[109],"mutations":[110],"specifically":[111],"commutative":[112],"operand":[113],"swapping,":[114],"independent":[115],"statement":[116],"reordering,":[117],"control":[119],"flow":[120],"morphing":[121],"proposed":[123],"embeds":[125],"cryptographically":[126],"verifiable":[127],"signatures":[128],"into":[129],"syntactic":[131],"topology":[132],"program":[135],"without":[136],"altering":[137],"functional":[138],"behavior":[139],"or":[140],"computational":[141],"Big-O":[142],"complexity.":[143],"Detection":[144],"is":[145],"executed":[146],"blind":[149],"statistical":[150],"extraction":[151],"engine":[152],"employing":[153],"one-proportion":[155],"Z-test":[156],"against":[157,190],"uniform":[159],"null":[160],"hypothesis.":[161],"Experimental":[162],"evaluation":[163],"across":[164,223],"benchmarks":[166],"demonstrates":[167],"AST-level":[170],"achieves":[172],"100.0%":[173],"detection":[174],"fidelity":[175],"on":[176],"formatted":[177],"code,":[178],"98.2%":[179],"true":[180],"positive":[181,207],"rate":[182,208],"under":[183],"aggressive":[184],"95.5%":[188],"resilience":[189],"dead":[191],"injection,":[193],"significantly":[194],"outperforming":[195],"state-of-the-art":[196],"logits-based":[197],"(UMD)":[198],"(SWEET)":[201],"baselines":[202],"maintaining":[204],"false":[206],"strictly":[209],"below":[210],"1.0%.":[211],"architecture":[213],"establishes":[214],"scalable,":[216],"model-agnostic":[217],"provenance":[218],"defense":[219],"suitable":[220],"for":[221],"deployment":[222],"enterprise":[224],"assistants.":[226]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-08-19T00:00:00"}