{"id":"https://openalex.org/W3044696307","doi":null,"title":"Scalable Inference of Symbolic Adversarial Examples.","display_name":"Scalable Inference of Symbolic Adversarial Examples.","publication_year":2020,"publication_date":"2020-07-23","ids":{"openalex":"https://openalex.org/W3044696307","mag":"3044696307"},"language":"en","primary_location":{"id":"mag:3044696307","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2007.12133","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://export.arxiv.org/pdf/2007.12133","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002442193","display_name":"Dimitar I. Dimitrov","orcid":"https://orcid.org/0000-0001-9813-0900","observed_orcids":["https://orcid.org/0000-0001-9813-0900","https://orcid.org/0000-0001-9393-0925"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dimitar I. Dimitrov","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-9813-0900","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100760604","display_name":"Gagandeep Singh","orcid":"https://orcid.org/0000-0002-9299-2961","observed_orcids":["https://orcid.org/0000-0002-9299-2961"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gagandeep Singh","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-9299-2961","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045044745","display_name":"Timon Gehr","orcid":"https://orcid.org/0009-0000-7470-0489","observed_orcids":["https://orcid.org/0009-0000-7470-0489"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Timon Gehr","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5069901599","display_name":"Martin Vechev","orcid":"https://orcid.org/0000-0002-0054-9568","observed_orcids":["https://orcid.org/0000-0002-0054-9568"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martin Vechev","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-0054-9568","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9990000128746033,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9990000128746033,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.0005000000237487257,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T11424","display_name":"Security and Verification in Computing","score":0.0003000000142492354,"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/adversarial-examples","display_name":"adversarial examples","score":0.7720000147819519},{"id":"https://openalex.org/keywords/neural-network-robustness","display_name":"neural network robustness","score":0.7379999756813049},{"id":"https://openalex.org/keywords/adversarial-attack-generation","display_name":"adversarial attack generation","score":0.4269999861717224},{"id":"https://openalex.org/keywords/convex-relaxation","display_name":"convex relaxation","score":0.9750000238418579},{"id":"https://openalex.org/keywords/scalable-inference","display_name":"scalable inference","score":0.6570000052452087}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.9016916751861572},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6928173303604126},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6305989027023315},{"id":"https://openalex.org/C140479938","wikidata":"https://www.wikidata.org/wiki/Q5254619","display_name":"Iterated function","level":2,"score":0.5868731737136841},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5528044700622559},{"id":"https://openalex.org/C68693459","wikidata":"https://www.wikidata.org/wiki/Q657586","display_name":"Hyperplane","level":2,"score":0.4719863533973694},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4640236496925354},{"id":"https://openalex.org/C2776029896","wikidata":"https://www.wikidata.org/wiki/Q3935810","display_name":"Relaxation (psychology)","level":2,"score":0.41150227189064026},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3759456276893616},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36767393350601196},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20626583695411682},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3044696307","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2007.12133","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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}],"best_oa_location":{"id":"mag:3044696307","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2007.12133","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2112796928","https://openalex.org/W2460937040","https://openalex.org/W2516574342","https://openalex.org/W2590523583","https://openalex.org/W2611576673","https://openalex.org/W2807040120","https://openalex.org/W2810611310","https://openalex.org/W2899434523","https://openalex.org/W2903571520","https://openalex.org/W2944621111","https://openalex.org/W2948854542","https://openalex.org/W2963207607","https://openalex.org/W2964153729","https://openalex.org/W2972413024","https://openalex.org/W2981016037","https://openalex.org/W2991240978","https://openalex.org/W2997223761","https://openalex.org/W3005260693","https://openalex.org/W3007305010","https://openalex.org/W3035345420","https://openalex.org/W3118608800","https://openalex.org/W3130326051","https://openalex.org/W7019762664"],"related_works":["https://openalex.org/W2994715219","https://openalex.org/W6966345260","https://openalex.org/W2945047021","https://openalex.org/W6948665307","https://openalex.org/W7203768848","https://openalex.org/W2963557656","https://openalex.org/W3005093931","https://openalex.org/W3093350053","https://openalex.org/W7161289876","https://openalex.org/W3199131392"],"abstract_inverted_index":{"We":[0,49],"present":[1,50],"a":[2,51,58,70,92,126],"novel":[3],"method":[4,52,62,119],"for":[5,18,53,96],"generating":[6],"symbolic":[7,43,93,132],"adversarial":[8,16,28,35,44,66,94,111,139],"examples:":[9],"input":[10],"regions":[11,24],"guaranteed":[12,134],"to":[13,68,130,135],"only":[14,109,124],"contain":[15,136],"examples":[17,29,45,56],"the":[19,107],"given":[20],"neural":[21],"network.":[22],"These":[23],"can":[25,99],"generate":[26,69],"real-world":[27],"as":[30],"they":[31],"summarize":[32],"trillions":[33],"of":[34],"examples.":[36,112,140],"\r\nWe":[37],"theoretically":[38],"show":[39],"that":[40,80,106,117],"computing":[41],"optimal":[42,55],"is":[46,120],"computationally":[47],"expensive.":[48],"approximating":[54],"in":[57],"scalable":[59],"manner.":[60],"Our":[61,113],"first":[63],"selectively":[64],"uses":[65],"attacks":[67,129],"candidate":[71],"region":[72,77,108],"and":[73],"then":[74],"prunes":[75],"this":[76],"with":[78],"hyperplanes":[79],"fit":[81],"points":[82],"obtained":[83],"via":[84,101],"specialized":[85],"sampling.":[86],"It":[87],"iterates":[88],"until":[89],"arriving":[90],"at":[91],"example":[95],"which":[97],"it":[98,123],"prove,":[100],"state-of-the-art":[102],"convex":[103],"relaxation":[104],"techniques,":[105],"contains":[110],"experimental":[114],"results":[115],"demonstrate":[116],"our":[118],"practically":[121],"effective:":[122],"needs":[125],"few":[127],"thousand":[128],"infer":[131],"summaries":[133],"$\\approx":[137],"10^{258}$":[138]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2020-07-29T00:00:00"}