{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T02:41:47Z","timestamp":1725763307833},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","funder":[{"name":"DARPA VSPELLS","award":["HR001120S0058"]},{"name":"IARPA TrojAI","award":["W911NF-19-S-0012"]},{"name":"NSF","award":["1901242, 1910300"]},{"name":"ONR","award":["N000141712045, N000141410468, N000141712947"]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,30]]},"DOI":"10.1145\/3611643.3616301","type":"proceedings-article","created":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T23:14:38Z","timestamp":1701386078000},"page":"401-412","update-policy":"http:\/\/dx.doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["PEM: Representing Binary Program Semantics for Similarity Analysis via a Probabilistic Execution Model"],"prefix":"10.1145","author":[{"ORCID":"http:\/\/orcid.org\/0000-0001-6619-781X","authenticated-orcid":false,"given":"Xiangzhe","family":"Xu","sequence":"first","affiliation":[{"name":"Purdue University, West Lafayette, USA"}]},{"ORCID":"http:\/\/orcid.org\/0009-0000-5738-885X","authenticated-orcid":false,"given":"Zhou","family":"Xuan","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, USA"}]},{"ORCID":"http:\/\/orcid.org\/0000-0001-6959-4327","authenticated-orcid":false,"given":"Shiwei","family":"Feng","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, USA"}]},{"ORCID":"http:\/\/orcid.org\/0009-0006-0903-6917","authenticated-orcid":false,"given":"Siyuan","family":"Cheng","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, USA"}]},{"ORCID":"http:\/\/orcid.org\/0000-0001-7232-0650","authenticated-orcid":false,"given":"Yapeng","family":"Ye","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, USA"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-8297-8998","authenticated-orcid":false,"given":"Qingkai","family":"Shi","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, USA"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-4701-1327","authenticated-orcid":false,"given":"Guanhong","family":"Tao","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, USA"}]},{"ORCID":"http:\/\/orcid.org\/0009-0008-7613-946X","authenticated-orcid":false,"given":"Le","family":"Yu","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, USA"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-6515-0021","authenticated-orcid":false,"given":"Zhuo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, USA"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-9544-2500","authenticated-orcid":false,"given":"Xiangyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, USA"}]}],"member":"320","published-online":{"date-parts":[[2023,11,30]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"2022. Learn the architecture - AArch64 Instruction Set Architecture. https:\/\/developer.arm.com\/documentation\/102374\/latest\/"},{"volume-title":"Dos and Don\u2019ts of Machine Learning in Computer Security. CoRR, abs\/2010.09470","year":"2020","author":"Arp Daniel","key":"e_1_3_2_2_2_1","unstructured":"Daniel Arp, Erwin Quiring, Feargus Pendlebury, Alexander Warnecke, Fabio Pierazzi, Christian Wressnegger, Lorenzo Cavallaro, and Konrad Rieck. 2020. Dos and Don\u2019ts of Machine Learning in Computer Security. CoRR, abs\/2010.09470 (2020), arXiv:2010.09470. arxiv:2010.09470"},{"volume-title":"23rd USENIX Security Symposium (USENIX Security 14)","year":"2014","author":"Bao Tiffany","key":"e_1_3_2_2_3_1","unstructured":"Tiffany Bao, Jonathan Burket, Maverick Woo, Rafael Turner, and David Brumley. 2014. BYTEWEIGHT: Learning to recognize functions in binary code. In 23rd USENIX Security Symposium (USENIX Security 14). 845\u2013860."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2420950.2420969"},{"key":"e_1_3_2_2_5_1","unstructured":"2022. zynamics BinDiff. https:\/\/www.zynamics.com\/bindiff.html"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2505515.2507848"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2950290.2950350"},{"key":"e_1_3_2_2_8_1","unstructured":"2022. Coreutils - GNU core utilities. https:\/\/www.gnu.org\/software\/coreutils\/"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2908080.2908126"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00003"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","unstructured":"Yue Duan Xuezixiang Li Jinghan Wang and Heng Yin. 2020. DeepBinDiff: Learning Program-Wide Code Representations for Binary Diffing. https:\/\/doi.org\/10.14722\/ndss.2020.24311 10.14722\/ndss.2020.24311","DOI":"10.14722\/ndss.2020.24311"},{"volume-title":"Proceedings of the 23rd USENIX Conference on Security Symposium (SEC\u201914)","year":"2014","author":"Egele Manuel","key":"e_1_3_2_2_12_1","unstructured":"Manuel Egele, Maverick Woo, Peter Chapman, and David Brumley. 2014. Blanket Execution: Dynamic Similarity Testing for Program Binaries and Components. In Proceedings of the 23rd USENIX Conference on Security Symposium (SEC\u201914). USENIX Association, USA. 303\u2013317. isbn:9781931971157"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978370"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2016.30"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3240480"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME.2018.00019"},{"volume-title":"Statistics: Continuous Multivariate Distributions","year":"1972","author":"Johnson N. L.","key":"e_1_3_2_2_17_1","unstructured":"N. L. Johnson and S. Kotz. 1972. Distributions in Statistics: Continuous Multivariate Distributions. John Wiley, New York, NY."},{"volume-title":"23rd USENIX Security Symposium (USENIX Security 14)","year":"2014","author":"Kapravelos Alexandros","key":"e_1_3_2_2_18_1","unstructured":"Alexandros Kapravelos, Chris Grier, Neha Chachra, Christopher Kruegel, Giovanni Vigna, and Vern Paxson. 2014. Hulk: Eliciting malicious behavior in browser extensions. In 23rd USENIX Security Symposium (USENIX Security 14)."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/SANER.2018.8330221"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2017.8115647"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-20550-2_1"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2022.3187689"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3533767.3534383"},{"volume-title":"Graph Matching Networks for Learning the Similarity of Graph Structured Objects. CoRR, abs\/1904.12787","year":"2019","author":"Li Yujia","key":"e_1_3_2_2_24_1","unstructured":"Yujia Li, Chenjie Gu, Thomas Dullien, Oriol Vinyals, and Pushmeet Kohli. 2019. Graph Matching Networks for Learning the Similarity of Graph Structured Objects. CoRR, abs\/1904.12787 (2019), arXiv:1904.12787. arxiv:1904.12787"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3238199"},{"key":"e_1_3_2_2_26_1","unstructured":"2022. llvm-project. https:\/\/github.com\/llvm\/llvm-project\/blob\/release\/12.x\/llvm\/lib\/Transforms\/Scalar\/ConstraintElimination.cpp"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2017.2655046"},{"volume-title":"USENIX 2022, 31st USENIX Security Symposium","year":"2022","author":"Marcelli Andrea","key":"e_1_3_2_2_28_1","unstructured":"Andrea Marcelli, Mariano Graziano, Xabier Ugarte-Pedrero, Yanick Fratantonio, Mohamad Mansouri, and Davide Balzarotti. 2022. How machine learning is solving the binary function similarity problem. In USENIX 2022, 31st USENIX Security Symposium, 10-12 August 2022, Boston, MA, USA, Usenix (Ed.). Boston."},{"volume-title":"Applying CodeBERT for Automated Program Repair of Java Simple Bugs. CoRR, abs\/2103.11626","year":"2021","author":"Mashhadi Ehsan","key":"e_1_3_2_2_29_1","unstructured":"Ehsan Mashhadi and Hadi Hemmati. 2021. Applying CodeBERT for Automated Program Repair of Java Simple Bugs. CoRR, abs\/2103.11626 (2021), arXiv:2103.11626. arxiv:2103.11626"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1811.05296"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2012.08680"},{"volume-title":"Proceedings of the 23rd USENIX Conference on Security Symposium (SEC\u201914)","year":"2014","author":"Peng Fei","key":"e_1_3_2_2_32_1","unstructured":"Fei Peng, Zhui Deng, Xiangyu Zhang, Dongyan Xu, Zhiqiang Lin, and Zhendong Su. 2014. X-Force: Force-Executing Binary Programs for Security Applications. In Proceedings of the 23rd USENIX Conference on Security Symposium (SEC\u201914). USENIX Association, USA. 829\u2013844. isbn:9781931971157"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2015.49"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2664243.2664269"},{"key":"e_1_3_2_2_35_1","unstructured":"2023. A generic and open source machine emulator and virtualizer. https:\/\/www.qemu.org"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3453483.3454035"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510227"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2884781.2884877"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3412376"},{"volume-title":"24th USENIX Security Symposium (USENIX Security 15)","year":"2015","author":"Richard Shin Eui Chul","key":"e_1_3_2_2_40_1","unstructured":"Eui Chul Richard Shin, Dawn Song, and Reza Moazzezi. 2015. Recognizing functions in binaries with neural networks. In 24th USENIX Security Symposium (USENIX Security 15). 611\u2013626."},{"volume-title":"CoRR, abs\/1706.03762","year":"2017","author":"Vaswani Ashish","key":"e_1_3_2_2_41_1","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention Is All You Need. CoRR, abs\/1706.03762 (2017), arXiv:1706.03762. arxiv:1706.03762"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3381307.3381310"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.5555\/3155562.3155606"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597926.3598121"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3134018"},{"key":"e_1_3_2_2_46_1","unstructured":"Xiangzhe Xu Zhou Xuan Shiwei Feng Siyuan Cheng Yapeng Ye Qingkai Shi Guanhong Tao Le Yu Zhuo Zhang and Xiangyu Zhang. 2023. PEM. https:\/\/github.com\/XZ-X\/PEM.git"},{"volume-title":"PEM: Representing Binary Program Semantics for Similarity Analysis via a Probabilistic Execution Model. arxiv:2308.15449.","year":"2023","author":"Xu Xiangzhe","key":"e_1_3_2_2_47_1","unstructured":"Xiangzhe Xu, Zhou Xuan, Shiwei Feng, Siyuan Cheng, Yapeng Ye, Qingkai Shi, Guanhong Tao, Le Yu, Zhuo Zhang, and Xiangyu Zhang. 2023. PEM: Representing Binary Program Semantics for Similarity Analysis via a Probabilistic Execution Model. arxiv:2308.15449."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","unstructured":"Xi Xu Qinghua Zheng Ming Fan Jia Ang and Ting Liu. 2021. Interpretation-enabled Software Reuse Detection Based on a Multi-Level Birthmark Model. 873\u2013884. https:\/\/doi.org\/10.1109\/ICSE43902.2021.00084 10.1109\/ICSE43902.2021.00084","DOI":"10.1109\/ICSE43902.2021.00084"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2017.49"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2021.3056139"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP40000.2020.00035"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5466"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/1134285.1134324"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00051"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3360563"}],"event":{"name":"ESEC\/FSE '23: 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"],"location":"San Francisco CA USA","acronym":"ESEC\/FSE '23"},"container-title":["Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3611643.3616301","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,28]],"date-time":"2024-05-28T18:13:14Z","timestamp":1716919994000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3611643.3616301"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,30]]},"references-count":55,"alternative-id":["10.1145\/3611643.3616301","10.1145\/3611643"],"URL":"https:\/\/doi.org\/10.1145\/3611643.3616301","relation":{},"subject":[],"published":{"date-parts":[[2023,11,30]]},"assertion":[{"value":"2023-11-30","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}