{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T09:05:34Z","timestamp":1770282334552,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,8,18]],"date-time":"2021-08-18T00:00:00Z","timestamp":1629244800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,8,20]]},"DOI":"10.1145\/3468264.3468532","type":"proceedings-article","created":{"date-parts":[[2021,8,19]],"date-time":"2021-08-19T01:44:18Z","timestamp":1629337458000},"page":"806-817","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["TaintStream: fine-grained taint tracking for big data platforms through dynamic code translation"],"prefix":"10.1145","author":[{"given":"Chengxu","family":"Yang","sequence":"first","affiliation":[{"name":"Peking University, China"}]},{"given":"Yuanchun","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft Research, China"}]},{"given":"Mengwei","family":"Xu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, China"}]},{"given":"Zhenpeng","family":"Chen","sequence":"additional","affiliation":[{"name":"Peking University, China"}]},{"given":"Yunxin","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University, China"}]},{"given":"Gang","family":"Huang","sequence":"additional","affiliation":[{"name":"Peking University, China"}]},{"given":"Xuanzhe","family":"Liu","sequence":"additional","affiliation":[{"name":"Peking University, China"}]}],"member":"320","published-online":{"date-parts":[[2021,8,18]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"principles, techniques. Addison wesley, 7, 8","author":"Aho Alfred V","year":"1986","unstructured":"Alfred V Aho , Ravi Sethi , and Jeffrey D Ullman . 1986. Compilers , principles, techniques. Addison wesley, 7, 8 ( 1986 ), 9. Alfred V Aho, Ravi Sethi, and Jeffrey D Ullman. 1986. Compilers, principles, techniques. Addison wesley, 7, 8 (1986), 9."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2742797"},{"key":"e_1_3_2_1_3_1","volume-title":"https:\/\/github.com\/secure-software-engineering\/DroidBench Accessed February 4th","author":"Arzt Steven","year":"2021","unstructured":"Steven Arzt . 2021. DroidBench 2.0. https:\/\/github.com\/secure-software-engineering\/DroidBench Accessed February 4th , 2021 . Steven Arzt. 2021. DroidBench 2.0. https:\/\/github.com\/secure-software-engineering\/DroidBench Accessed February 4th, 2021."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2594291.2594299"},{"key":"e_1_3_2_1_5_1","unstructured":"Python Code Quality Authority. 2021. Astroid\u2019s documentation. http:\/\/pylint.pycqa.org\/projects\/astroid\/en\/latest\/ Accessed February 25 2021.  Python Code Quality Authority. 2021. Astroid\u2019s documentation. http:\/\/pylint.pycqa.org\/projects\/astroid\/en\/latest\/ Accessed February 25 2021."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-54792-8_9"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2016.07.001"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1706299.1706349"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2462410.2462423"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1542476.1542483"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1273463.1273490"},{"key":"e_1_3_2_1_12_1","first-page":"12","article-title":"DBTaint: Cross-Application Information Flow Tracking via Databases","volume":"10","author":"Davis Benjamin","year":"2010","unstructured":"Benjamin Davis and Hao Chen . 2010 . DBTaint: Cross-Application Information Flow Tracking via Databases .. WebApps , 10 (2010), 12 . Benjamin Davis and Hao Chen. 2010. DBTaint: Cross-Application Information Flow Tracking via Databases.. WebApps, 10 (2010), 12.","journal-title":"WebApps"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2619091"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2010.2051393"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2660267.2660343"},{"key":"e_1_3_2_1_16_1","volume-title":"https:\/\/pyre-check.org\/docs\/pysa-basics\/ Accessed February 4th","author":"Overview PySa","year":"2021","unstructured":"Facebook. 2021. PySa Overview . https:\/\/pyre-check.org\/docs\/pysa-basics\/ Accessed February 4th , 2021 . Facebook. 2021. PySa Overview. https:\/\/pyre-check.org\/docs\/pysa-basics\/ Accessed February 4th, 2021."},{"key":"e_1_3_2_1_17_1","volume-title":"Welcome to Faker\u2019s documentation!. https:\/\/faker.readthedocs.io\/en\/master\/ Accessed February 4th","author":"Faraglia Daniele","year":"2021","unstructured":"Daniele Faraglia . 2021. Welcome to Faker\u2019s documentation!. https:\/\/faker.readthedocs.io\/en\/master\/ Accessed February 4th , 2021 . Daniele Faraglia. 2021. Welcome to Faker\u2019s documentation!. https:\/\/faker.readthedocs.io\/en\/master\/ Accessed February 4th, 2021."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037739"},{"key":"e_1_3_2_1_19_1","volume-title":"https:\/\/storm.apache.org\/ Accessed","author":"Foundation Apache Software","year":"2020","unstructured":"Apache Software Foundation . 2021. Apache Storm . https:\/\/storm.apache.org\/ Accessed December 16, 2020 . Apache Software Foundation. 2021. Apache Storm. https:\/\/storm.apache.org\/ Accessed December 16, 2020."},{"key":"e_1_3_2_1_20_1","volume-title":"Taintassembly: Taint-based information flow control tracking for webassembly. arXiv preprint arXiv:1802.01050.","author":"Fu William","year":"2018","unstructured":"William Fu , Raymond Lin , and Daniel Inge . 2018 . Taintassembly: Taint-based information flow control tracking for webassembly. arXiv preprint arXiv:1802.01050. William Fu, Raymond Lin, and Daniel Inge. 2018. Taintassembly: Taint-based information flow control tracking for webassembly. arXiv preprint arXiv:1802.01050."},{"key":"e_1_3_2_1_21_1","volume-title":"Hails: Protecting data privacy in untrusted web applications. In 10th $USENIX$ Symposium on Operating Systems Design and Implementation (OSDI 12). 47\u201360.","author":"Giffin Daniel B","year":"2012","unstructured":"Daniel B Giffin , Amit Levy , Deian Stefan , David Terei , David Mazieres , John C Mitchell , and Alejandro Russo . 2012 . Hails: Protecting data privacy in untrusted web applications. In 10th $USENIX$ Symposium on Operating Systems Design and Implementation (OSDI 12). 47\u201360. Daniel B Giffin, Amit Levy, Deian Stefan, David Terei, David Mazieres, John C Mitchell, and Alejandro Russo. 2012. Hails: Protecting data privacy in untrusted web applications. In 10th $USENIX$ Symposium on Operating Systems Design and Implementation (OSDI 12). 47\u201360."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2001420.2001442"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2771783.2771803"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-016-0059-y"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2025113.2025125"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/512927.512945"},{"key":"e_1_3_2_1_27_1","first-page":"1","article-title":"Kafka: A distributed messaging system for log processing","volume":"11","author":"Kreps Jay","year":"2011","unstructured":"Jay Kreps , Neha Narkhede , and Jun Rao . 2011 . Kafka: A distributed messaging system for log processing . In Proceedings of the NetDB. 11 , 1 \u2013 7 . Jay Kreps, Neha Narkhede, and Jun Rao. 2011. Kafka: A distributed messaging system for log processing. In Proceedings of the NetDB. 11, 1\u20137.","journal-title":"Proceedings of the NetDB."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3130941"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2016.2558446"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/363516.363526"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/AINA.2014.139"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/596980.596983"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2002.806121"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/AINA.2016.127"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2010.26"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2014.28"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSST.2010.5496972"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/1242572.1242599"},{"key":"e_1_3_2_1_39_1","unstructured":"Apache Spark. 2021. Document of PySpark SQL module.. http:\/\/spark.apache.org\/docs\/latest\/api\/python\/pyspark.sql.html Accessed February 21 2021.  Apache Spark. 2021. Document of PySpark SQL module.. http:\/\/spark.apache.org\/docs\/latest\/api\/python\/pyspark.sql.html Accessed February 21 2021."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2048066.2048145"},{"key":"e_1_3_2_1_41_1","volume-title":"https:\/\/github.com\/too4words\/securibench-micro Accessed February 4th","author":"Micro Securibench","year":"2021","unstructured":"Stanford. 2021. Securibench Micro . https:\/\/github.com\/too4words\/securibench-micro Accessed February 4th , 2021 . Stanford. 2021. Securibench Micro. https:\/\/github.com\/too4words\/securibench-micro Accessed February 4th, 2021."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978343"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421292"},{"key":"e_1_3_2_1_44_1","unstructured":"TPC. 2021. TPCx-BB is a Big Data Benchmark. http:\/\/www.tpc.org\/tpcx-bb\/ Accessed December 17 2020.  TPC. 2021. TPCx-BB is a Big Data Benchmark. http:\/\/www.tpc.org\/tpcx-bb\/ Accessed December 17 2020."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2012.21"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037744"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-33752-0_1"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3243734.3243835"},{"key":"e_1_3_2_1_49_1","volume-title":"Children\u2019s Online Privacy Protection Act. https:\/\/en.wikipedia.org\/wiki\/Children%27s_Online_Privacy_Protection_Act Accessed","year":"2021","unstructured":"Wikipedia. 2021. Children\u2019s Online Privacy Protection Act. https:\/\/en.wikipedia.org\/wiki\/Children%27s_Online_Privacy_Protection_Act Accessed February 13, 2021 . Wikipedia. 2021. Children\u2019s Online Privacy Protection Act. https:\/\/en.wikipedia.org\/wiki\/Children%27s_Online_Privacy_Protection_Act Accessed February 13, 2021."},{"key":"e_1_3_2_1_50_1","volume-title":"General Data Protection Regulation. https:\/\/en.wikipedia.org\/wiki\/General_Data_Protection_Regulation Accessed","year":"2021","unstructured":"Wikipedia. 2021. General Data Protection Regulation. https:\/\/en.wikipedia.org\/wiki\/General_Data_Protection_Regulation Accessed February 13, 2021 . Wikipedia. 2021. General Data Protection Regulation. https:\/\/en.wikipedia.org\/wiki\/General_Data_Protection_Regulation Accessed February 13, 2021."},{"key":"e_1_3_2_1_51_1","volume-title":"Health Insurance Portability and Accountability Act. https:\/\/en.wikipedia.org\/wiki\/Health_Insurance_Portability_and_Accountability_Act Accessed","year":"2021","unstructured":"Wikipedia. 2021. Health Insurance Portability and Accountability Act. https:\/\/en.wikipedia.org\/wiki\/Health_Insurance_Portability_and_Accountability_Act Accessed February 13, 2021 . Wikipedia. 2021. Health Insurance Portability and Accountability Act. https:\/\/en.wikipedia.org\/wiki\/Health_Insurance_Portability_and_Accountability_Act Accessed February 13, 2021."},{"key":"e_1_3_2_1_52_1","volume-title":"21st USENIX Security Symposium (USENIX Security 12)","author":"Yan Lok Kwong","year":"2012","unstructured":"Lok Kwong Yan and Heng Yin . 2012 . Droidscope: Seamlessly reconstructing the OS and dalvik semantic views for dynamic android malware analysis . In 21st USENIX Security Symposium (USENIX Security 12) . 569\u2013584. Lok Kwong Yan and Heng Yin. 2012. Droidscope: Seamlessly reconstructing the OS and dalvik semantic views for dynamic android malware analysis. In 21st USENIX Security Symposium (USENIX Security 12). 569\u2013584."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/2103621.2103669"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/WCSE.2012.26"},{"key":"e_1_3_2_1_55_1","first-page":"10","article-title":"Spark: Cluster computing with working sets","volume":"10","author":"Zaharia Matei","year":"2010","unstructured":"Matei Zaharia , Mosharaf Chowdhury , Michael J Franklin , Scott Shenker , and Ion Stoica . 2010 . Spark: Cluster computing with working sets .. HotCloud , 10 , 10 - 10 (2010), 95. Matei Zaharia, Mosharaf Chowdhury, Michael J Franklin, Scott Shenker, and Ion Stoica. 2010. Spark: Cluster computing with working sets.. HotCloud, 10, 10-10 (2010), 95.","journal-title":"HotCloud"}],"event":{"name":"ESEC\/FSE '21: 29th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","location":"Athens Greece","acronym":"ESEC\/FSE '21","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3468264.3468532","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3468264.3468532","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:24:50Z","timestamp":1750195490000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3468264.3468532"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,18]]},"references-count":55,"alternative-id":["10.1145\/3468264.3468532","10.1145\/3468264"],"URL":"https:\/\/doi.org\/10.1145\/3468264.3468532","relation":{},"subject":[],"published":{"date-parts":[[2021,8,18]]},"assertion":[{"value":"2021-08-18","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}