{"id":"https://openalex.org/W4406458650","doi":"https://doi.org/10.1109/bigdata62323.2024.10825125","title":"Causal Tracing to Identify Hacking Knowledge in Large Language Models","display_name":"Causal Tracing to Identify Hacking Knowledge in Large Language Models","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406458650","doi":"https://doi.org/10.1109/bigdata62323.2024.10825125"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825125","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825125","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5001644977","display_name":"Ryan Marinelli","orcid":null},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":true,"raw_author_name":"Ryan Marinelli","raw_affiliation_strings":["University of Oslo,Department of Informatics,Oslo,Norway"],"affiliations":[{"raw_affiliation_string":"University of Oslo,Department of Informatics,Oslo,Norway","institution_ids":["https://openalex.org/I184942183"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5001644977"],"corresponding_institution_ids":["https://openalex.org/I184942183"],"apc_list":null,"apc_paid":null,"fwci":0.3637,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.70831698,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"8774","last_page":"8776"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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/T10181","display_name":"Natural Language Processing Techniques","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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9830999970436096,"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/computer-science","display_name":"Computer science","score":0.7349212169647217},{"id":"https://openalex.org/keywords/hacker","display_name":"Hacker","score":0.7300454378128052},{"id":"https://openalex.org/keywords/tracing","display_name":"Tracing","score":0.6163476705551147},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37942174077033997},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37041398882865906},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.34335657954216003},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20079874992370605},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.18334844708442688}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7349212169647217},{"id":"https://openalex.org/C86844869","wikidata":"https://www.wikidata.org/wiki/Q2798820","display_name":"Hacker","level":2,"score":0.7300454378128052},{"id":"https://openalex.org/C138673069","wikidata":"https://www.wikidata.org/wiki/Q322229","display_name":"Tracing","level":2,"score":0.6163476705551147},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37942174077033997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37041398882865906},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.34335657954216003},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20079874992370605},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.18334844708442688}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825125","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825125","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2295124130","https://openalex.org/W3118781290","https://openalex.org/W4281657280","https://openalex.org/W4389768263","https://openalex.org/W4390092558","https://openalex.org/W6788175385","https://openalex.org/W6839328737","https://openalex.org/W6859670380","https://openalex.org/W6859821825"],"related_works":["https://openalex.org/W2921504876","https://openalex.org/W2183730421","https://openalex.org/W1982580243","https://openalex.org/W2551868243","https://openalex.org/W2348153269","https://openalex.org/W4205613068","https://openalex.org/W3112956360","https://openalex.org/W2004781009","https://openalex.org/W4286284259","https://openalex.org/W3204019825"],"abstract_inverted_index":{"This":[0],"research":[1],"seeks":[2],"to":[3,81,88],"identify":[4],"where":[5],"hacking":[6],"knowledge":[7,38,64],"is":[8,14,33,51],"stored":[9],"in":[10,43],"models.":[11],"SQL":[12,36,62],"Injection":[13,37,63],"used":[15],"as":[16],"a":[17,69],"base":[18],"case":[19],"considering":[20],"the":[21,44,48,74],"risks":[22],"involved":[23],"with":[24],"production":[25],"systems.":[26],"Through":[27],"using":[28],"causal":[29],"tracing":[30],"techniques,":[31],"it":[32,85],"determined":[34],"that":[35,54],"capabilities":[39],"are":[40],"most":[41],"prevalent":[42],"last":[45],"layers":[46],"of":[47,61],"network.":[49],"It":[50],"also":[52],"established":[53],"there":[55],"may":[56],"be":[57,89],"some":[58],"shared":[59],"representation":[60],"across":[65],"models":[66],"through":[67],"training":[68,73],"KNN":[70],"classifier.":[71],"When":[72],"classifier":[75],"on":[76,83],"GPT-Neo\u2019s":[77],"activations":[78],"and":[79],"attempting":[80],"classify":[82],"GPT-2,":[84],"was":[86],"found":[87],"52%":[90],"accurate.":[91]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}