{"id":"https://openalex.org/W3106995303","doi":"https://doi.org/10.1145/3468264.3468545","title":"Probing model signal-awareness via prediction-preserving input minimization","display_name":"Probing model signal-awareness via prediction-preserving input minimization","publication_year":2021,"publication_date":"2021-08-18","ids":{"openalex":"https://openalex.org/W3106995303","doi":"https://doi.org/10.1145/3468264.3468545","mag":"3106995303"},"language":"en","primary_location":{"id":"doi:10.1145/3468264.3468545","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3468264.3468545","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.14934","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034331643","display_name":"Sahil Suneja","orcid":"https://orcid.org/0009-0005-5094-5779"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sahil Suneja","raw_affiliation_strings":["IBM Research, USA","IBM"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, USA","institution_ids":[]},{"raw_affiliation_string":"IBM","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039824895","display_name":"Yunhui Zheng","orcid":"https://orcid.org/0000-0002-6794-3199"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunhui Zheng","raw_affiliation_strings":["IBM Research, USA","IBM"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, USA","institution_ids":[]},{"raw_affiliation_string":"IBM","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052671723","display_name":"Yufan Zhuang","orcid":"https://orcid.org/0000-0003-4063-6460"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yufan Zhuang","raw_affiliation_strings":["IBM Research, USA","IBM"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, USA","institution_ids":[]},{"raw_affiliation_string":"IBM","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090845035","display_name":"Jim Laredo","orcid":"https://orcid.org/0000-0002-4915-0304"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jim A. Laredo","raw_affiliation_strings":["IBM Research, USA","IBM"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, USA","institution_ids":[]},{"raw_affiliation_string":"IBM","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076968229","display_name":"Alessandro Morari","orcid":"https://orcid.org/0009-0005-5006-8817"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alessandro Morari","raw_affiliation_strings":["IBM Research, USA","IBM"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, USA","institution_ids":[]},{"raw_affiliation_string":"IBM","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.569,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.70677461,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"945","last_page":"955"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9983999729156494,"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":0.9983999729156494,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.994700014591217,"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"}},{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9879000186920166,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/computer-science","display_name":"Computer science","score":0.7665277123451233},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6450462937355042},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5920984745025635},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5806975960731506},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5316404104232788},{"id":"https://openalex.org/keywords/snippet","display_name":"Snippet","score":0.5161508321762085},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5036932826042175},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.5024282932281494},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4934488832950592},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.44587376713752747},{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.43748950958251953},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42351624369621277},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3565278649330139},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.14114239811897278},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.08218023180961609}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7665277123451233},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6450462937355042},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5920984745025635},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5806975960731506},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5316404104232788},{"id":"https://openalex.org/C2777822670","wikidata":"https://www.wikidata.org/wiki/Q1120538","display_name":"Snippet","level":2,"score":0.5161508321762085},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5036932826042175},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.5024282932281494},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4934488832950592},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.44587376713752747},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.43748950958251953},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42351624369621277},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3565278649330139},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.14114239811897278},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.08218023180961609},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3468264.3468545","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3468264.3468545","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2011.14934","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.14934","pdf_url":"https://arxiv.org/pdf/2011.14934","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3106995303","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2011.14934.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2011.14934","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.14934","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.14934","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.14934","pdf_url":"https://arxiv.org/pdf/2011.14934","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3106995303.pdf","grobid_xml":"https://content.openalex.org/works/W3106995303.grobid-xml"},"referenced_works_count":71,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1924770834","https://openalex.org/W1968847337","https://openalex.org/W1988918904","https://openalex.org/W1992114977","https://openalex.org/W2010608861","https://openalex.org/W2064675550","https://openalex.org/W2121081915","https://openalex.org/W2121217767","https://openalex.org/W2159613309","https://openalex.org/W2164582878","https://openalex.org/W2170224888","https://openalex.org/W2194775991","https://openalex.org/W2243397390","https://openalex.org/W2282821441","https://openalex.org/W2293634267","https://openalex.org/W2295107390","https://openalex.org/W2296324027","https://openalex.org/W2407776548","https://openalex.org/W2460937040","https://openalex.org/W2516621648","https://openalex.org/W2519887557","https://openalex.org/W2535873859","https://openalex.org/W2592097190","https://openalex.org/W2594633041","https://openalex.org/W2605409611","https://openalex.org/W2606780347","https://openalex.org/W2624094989","https://openalex.org/W2765813195","https://openalex.org/W2766856748","https://openalex.org/W2781491433","https://openalex.org/W2788512147","https://openalex.org/W2889225139","https://openalex.org/W2890991187","https://openalex.org/W2891185194","https://openalex.org/W2917321477","https://openalex.org/W2945033152","https://openalex.org/W2950898568","https://openalex.org/W2953106684","https://openalex.org/W2962858109","https://openalex.org/W2962862931","https://openalex.org/W2962960733","https://openalex.org/W2962995178","https://openalex.org/W2963207607","https://openalex.org/W2963499994","https://openalex.org/W2963857521","https://openalex.org/W2963858333","https://openalex.org/W2964121744","https://openalex.org/W2964153729","https://openalex.org/W2964180856","https://openalex.org/W2964253222","https://openalex.org/W2967556797","https://openalex.org/W2970119293","https://openalex.org/W2970862273","https://openalex.org/W2972317931","https://openalex.org/W2979792666","https://openalex.org/W2986734036","https://openalex.org/W3008797115","https://openalex.org/W3035171481","https://openalex.org/W3036453007","https://openalex.org/W3086100325","https://openalex.org/W3086449553","https://openalex.org/W3090988182","https://openalex.org/W3101228802","https://openalex.org/W3109966548","https://openalex.org/W3127736190","https://openalex.org/W3163206498","https://openalex.org/W3168488662","https://openalex.org/W6600497981","https://openalex.org/W6601796474","https://openalex.org/W6604896550"],"related_works":["https://openalex.org/W3194682511","https://openalex.org/W2901762548","https://openalex.org/W2742890997","https://openalex.org/W3034218934","https://openalex.org/W3004430916","https://openalex.org/W2990559773","https://openalex.org/W3169447391","https://openalex.org/W2778718264","https://openalex.org/W2903713146","https://openalex.org/W2950868217","https://openalex.org/W2963223515","https://openalex.org/W2948777210","https://openalex.org/W2497344197","https://openalex.org/W2966441378","https://openalex.org/W2753723464","https://openalex.org/W3209497701","https://openalex.org/W3127156819","https://openalex.org/W2971056844","https://openalex.org/W3211326283","https://openalex.org/W3211065546"],"abstract_inverted_index":{"This":[0],"work":[1],"explores":[2],"the":[3,22,27,43,69,72,78,84,93,127,131,137,142,162,185,203,216,230,234],"signal":[4,94],"awareness":[5,95],"of":[6,82,96,150,187,205],"AI":[7],"models":[8,97,143],"for":[9,224],"source":[10,45],"code":[11,46,74],"understanding.":[12],"Using":[13],"a":[14,48,52,99,123,148,188,192,213],"software":[15],"vulnerability":[16,29,70,158],"detection":[17,159],"use":[18],"case,":[19],"we":[20,102],"evaluate":[21],"models'":[23],"ability":[24],"to":[25,31,47,55,134,183,201,211,226],"capture":[26],"correct":[28],"signals":[30,64],"produce":[32],"their":[33,157],"predictions.":[34],"Our":[35],"prediction-preserving":[36],"input":[37],"minimization":[38],"(P2IM)":[39],"approach":[40],"systematically":[41],"reduces":[42],"original":[44,73],"minimal":[49,79],"snippet":[50],"which":[51,83],"model":[53,85,165,190,207,235],"needs":[54],"maintain":[56],"its":[57],"prediction.":[58],"The":[59,120,179,219],"model's":[60,128],"reliance":[61],"on":[62,111],"incorrect":[63],"is":[65,75,181,200,223],"then":[66],"uncovered":[67],"when":[68],"in":[71,77,126,164,191,215,221,229],"missing":[76],"snippet,":[80],"both":[81],"however":[86],"predicts":[87],"as":[88,170],"being":[89],"vulnerable.":[90],"We":[91,108],"measure":[92,202],"using":[98],"new":[100,138],"metric":[101],"propose":[103],"--":[104],"Signal-aware":[105],"Recall":[106,129,217,228],"(SAR).":[107],"apply":[109],"P2IM":[110],"three":[112],"different":[113],"neural":[114],"network":[115],"architectures":[116],"across":[117],"multiple":[118],"datasets.":[119],"results":[121],"show":[122],"sharp":[124],"drop":[125,163],"from":[130],"high":[132],"90s":[133],"sub-60s":[135],"with":[136],"metric,":[139],"highlighting":[140],"that":[141],"are":[144],"presumably":[145],"picking":[146],"up":[147],"lot":[149],"noise":[151],"or":[152],"dataset":[153],"nuances":[154],"while":[155],"learning":[156],"logic.":[160],"Although":[161],"performance":[166],"may":[167],"be":[168],"perceived":[169],"an":[171],"adversarial":[172],"attack,":[173],"but":[174],"this":[175],"isn't":[176],"P2IM's":[177],"objective.":[178],"idea":[180],"rather":[182],"uncover":[184],"signal-awareness":[186],"black-box":[189],"data-driven":[193],"manner":[194],"via":[195],"controlled":[196],"queries.":[197],"SAR's":[198],"purpose":[199],"impact":[204],"task-agnostic":[206],"training,":[208],"and":[209],"not":[210],"suggest":[212],"shortcoming":[214],"metric.":[218],"expectation,":[220],"fact,":[222],"SAR":[225],"match":[227],"ideal":[231],"scenario":[232],"where":[233],"truly":[236],"captures":[237],"task-specific":[238],"signals.":[239]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}