{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T16:12:55Z","timestamp":1792080775520,"version":"4.4.0"},"reference-count":124,"publisher":"Association for Computing Machinery (ACM)","issue":"ISSTA","license":[{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nd\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. ACM Softw. Eng."],"published-print":{"date-parts":[[2025,6,22]]},"abstract":"<jats:p>\n                    Decompilers are widely used in reverse engineering (RE) to convert compiled executables into human-readable pseudocode and support various security analysis tasks. Existing decompilers, such as IDA Pro and Ghidra, focus on enhancing the\n                    <jats:italic toggle=\"yes\">readability<\/jats:italic>\n                    of decompiled code rather than its\n                    <jats:italic toggle=\"yes\">recompilability,<\/jats:italic>\n                    which limits further programmatic use, such as for CodeQL-based vulnerability analysis that requires compilable versions of the decompiled code. Recent LLM-based approaches for enhancing decompilation results, while useful for human RE analysts, unfortunately also follow the same path.\n                  <\/jats:p>\n                  <jats:p>\n                    In this paper, we explore, for the first time, how off-the-shelf large language models (LLMs) can be used to enable\n                    <jats:italic toggle=\"yes\">recompilable decompilation<\/jats:italic>\n                    \u2014automatically correcting decompiler outputs into compilable versions. We first show that this is non-trivial through a pilot study examining existing rule-based and LLM-based approaches. Based on the lessons learned, we design\n                    <jats:sc>DecLLM,<\/jats:sc>\n                    an iterative LLM-based repair loop that utilizes both static recompilation and dynamic runtime feedback as oracles to iteratively fix decompiler outputs. We test\n                    <jats:sc>DecLLM<\/jats:sc>\n                    on popular C benchmarks and real-world binaries using two mainstream LLMs, GPT-3.5 and GPT-4, and show that off-the-shelf LLMs can achieve an upper bound of around 70% recompilation success rate, i.e., 70 out of 100 originally non-recompilable decompiler outputs are now recompilable. We also demonstrate the practical applicability of the recompilable code for CodeQL-based vulnerability analysis, which is impossible to perform directly on binaries. For the remaining 30% of hard cases, we further delve into their errors to gain insights for future improvements in decompilation-oriented LLM design.\n                  <\/jats:p>","DOI":"10.1145\/3728958","type":"journal-article","created":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T10:52:56Z","timestamp":1750589576000},"page":"1841-1864","source":"Crossref","is-referenced-by-count":26,"title":["DecLLM: LLM-Augmented Recompilable Decompilation for Enabling Programmatic Use of Decompiled Code"],"prefix":"10.1145","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2583-0698","authenticated-orcid":false,"given":"Wai Kin","family":"Wong","sequence":"first","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3752-0718","authenticated-orcid":false,"given":"Daoyuan","family":"Wu","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1066-0331","authenticated-orcid":false,"given":"Huaijin","family":"Wang","sequence":"additional","affiliation":[{"name":"Ohio State University, Ohio, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9897-4086","authenticated-orcid":false,"given":"Zongjie","family":"Li","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7872-1129","authenticated-orcid":false,"given":"Zhibo","family":"Liu","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0866-0308","authenticated-orcid":false,"given":"Shuai","family":"Wang","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8200-7518","authenticated-orcid":false,"given":"Qiyi","family":"Tang","sequence":"additional","affiliation":[{"name":"Tencent Security Keen Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4154-2941","authenticated-orcid":false,"given":"Sen","family":"Nie","sequence":"additional","affiliation":[{"name":"Tencent Security Keen Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6842-7487","authenticated-orcid":false,"given":"Shi","family":"Wu","sequence":"additional","affiliation":[{"name":"Tencent Security Keen Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,6,22]]},"reference":[{"key":"e_1_3_1_1_2","unstructured":"2003. Coreutils. https:\/\/www.gnu.org\/software\/coreutils\/."},{"key":"e_1_3_1_2_2","unstructured":"2013. sigaction both struct and function. https:\/\/stackoverflow.com\/questions\/14213270."},{"key":"e_1_3_1_3_2","unstructured":"2014. Find the C++ STL functions in a binary. https:\/\/reverseengineering.stackexchange.com\/a\/3890."},{"key":"e_1_3_1_4_2","unstructured":"2014. Starcraft Reverse Engineered to run on ARM. https:\/\/news.ycombinator.com\/item?id=7372414."},{"key":"e_1_3_1_5_2","unstructured":"2016. DARPA. Cyber Grand Challenge. https:\/\/www.darpa.mil\/program\/cyber-grand-challenge\/."},{"key":"e_1_3_1_6_2","unstructured":"2017. cgc-challenge-corpus. https:\/\/github.com\/lungetech\/cgc-challenge-corpus."},{"key":"e_1_3_1_7_2","unstructured":"2019. IDA - ObjC - Meaning of _BYTE and dword_0? https:\/\/reverseengineering.stackexchange.com\/questions\/22708."},{"key":"e_1_3_1_8_2","unstructured":"2022. AN EXHAUSTIVELY ANALYZED IDB FOR COMLOOK. https:\/\/www.msreverseengineering.com\/blog\/2022\/1\/25\/an-exhaustively-analyzed-idb-for-comlook."},{"key":"e_1_3_1_9_2","unstructured":"2022. Examples and guides for using the OpenAI API. https:\/\/github.com\/openai\/openai-cookbook\/."},{"key":"e_1_3_1_10_2","unstructured":"2022. Gepetto. https:\/\/github.com\/JusticeRage\/Gepetto\/."},{"key":"e_1_3_1_11_2","unstructured":"2022. gpt-wpre. https:\/\/github.com\/moyix\/gpt-wpre\/."},{"key":"e_1_3_1_12_2","unstructured":"2022. OpenAI Models overview. https:\/\/platform.openai.com\/docs\/models\/overview."},{"key":"e_1_3_1_13_2","unstructured":"2023. ArithmeticWithExtremeValues for CWE-190. https:\/\/github.com\/github\/codeql\/blob\/main\/cpp\/ql\/src\/Security\/CWE\/CWE-190\/ArithmeticWithExtremeValues.ql."},{"key":"e_1_3_1_14_2","unstructured":"2023. GPT-3.5. https:\/\/platform.openai.com\/docs\/models\/gpt-3-5."},{"key":"e_1_3_1_15_2","unstructured":"2023. How Long Can Open-Source LLMs Truly Promise on Context Length? https:\/\/lmsys.org\/blog\/2023-06-29-longchat\/."},{"key":"e_1_3_1_16_2","unstructured":"2023. LLM forgetting part of my prompt with too much data. https:\/\/community.openai.com\/t\/244698."},{"key":"e_1_3_1_17_2","unstructured":"2023. tiktoken. https:\/\/github.com\/openai\/tiktoken."},{"key":"e_1_3_1_18_2","unstructured":"2023. UseAfterFree.ql miss case 00. https:\/\/github.com\/github\/codeql\/issues\/13896."},{"key":"e_1_3_1_19_2","unstructured":"2024. Empty output in slightly more complex prompt. https:\/\/github.com\/albertan017\/LLM4Decompile\/issues\/15."},{"key":"e_1_3_1_20_2","unstructured":"2024. Question about ghidra\u2019s decompile.py file. https:\/\/github.com\/albertan017\/LLM4Decompile\/issues\/31."},{"key":"e_1_3_1_21_2","unstructured":"2025. AFLplusplus. https:\/\/github.com\/AFLplusplus\/AFLplusplus."},{"key":"e_1_3_1_22_2","unstructured":"2025. Artifact. https:\/\/sites.google.com\/view\/decllm."},{"key":"e_1_3_1_23_2","doi-asserted-by":"crossref","unstructured":"Anil Altinay Joseph Nash Taddeus Kroes Prabhu Rajasekaran Dixin Zhou Adrian Dabrowski David Gens Yeoul Na Stijn Volckaert Cristiano Giuffrida et al.. 2020. BinRec: dynamic binary lifting and recompilation. In Proceedings of the Fifteenth European Conference on Computer Systems. 1\u201316.","DOI":"10.1145\/3342195.3387550"},{"key":"e_1_3_1_24_2","unstructured":"Dennis Andriesse Xi Chen Victor Van Der Veen Asia Slowinska and Herbert Bos. 2016. An {In-Depth} Analysis of Disassembly on {Full-Scale} x86\/x64 Binaries. In 25th USENIX security symposium (USENIX security 16). 583\u2013600."},{"key":"e_1_3_1_25_2","unstructured":"Thomas Ball Shuo Chen and Cormac Herley. 2024. Can We Count on LLMs? The Fixed-Effect Fallacy and Claims of GPT-4 Capabilities. Transactions on Machine Learning Research. https:\/\/openreview.net\/forum?id=qt4d0EGZsK."},{"key":"e_1_3_1_26_2","unstructured":"Tiffany Bao Jonathan Burket Maverick Woo Rafael Turner and David Brumley. 2014. ByteWeight: Learning to Recognize Functions in Binary Code (USENIX Security)."},{"key":"e_1_3_1_27_2","doi-asserted-by":"crossref","unstructured":"Erick Bauman Zhiqiang Lin and Kevin W Hamlen. 2018. Superset Disassembly: Statically Rewriting x86 Binaries Without Heuristics.. In NDSS.","DOI":"10.14722\/ndss.2018.23300"},{"key":"e_1_3_1_28_2","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al.. 2020. Language models are few-shot learners. NeurIPS (2020)."},{"key":"e_1_3_1_29_2","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1109\/CGO.2003.1191551","volume-title":"International Symposium on Code Generation and Optimization, 2003. CGO 2003","author":"Bruening Derek","year":"2003","unstructured":"Derek Bruening, Timothy Garnett, and Saman Amarasinghe. 2003. An infrastructure for adaptive dynamic optimization. In International Symposium on Code Generation and Optimization, 2003. CGO 2003. IEEE, 265\u2013275."},{"key":"e_1_3_1_30_2","unstructured":"David Brumley JongHyup Lee Edward J. Schwartz and Maverick Woo. 2013. Native x86 Decompilation Using Semantics-Preserving Structural Analysis and Iterative Control-Flow Structuring. In Presented as part of the 22nd USENIX Security Symposium (USENIX Security 13). 353\u2013368."},{"key":"e_1_3_1_31_2","unstructured":"Kevin Burk Fabio Pagani Christopher Kruegel and Giovanni Vigna. 2022. Decomperson: How Humans Decompile and What We Can Learn From It. In 31st USENIX Security Symposium (USENIX Security 22). 2765\u20132782."},{"key":"e_1_3_1_32_2","doi-asserted-by":"crossref","unstructured":"Mahinthan Chandramohan Yinxing Xue Zhengzi Xu Yang Liu Chia Yuan Cho and Hee Beng Kuan Tan. 2016. Bingo: Cross-architecture cross-os binary search. In FSE.","DOI":"10.1145\/2950290.2950350"},{"key":"e_1_3_1_33_2","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1109\/DSN48063.2020.00028","volume-title":"2020 50th Annual IEEE\/IFIP International Conference on Dependable Systems and Networks (DSN)","author":"Chen Ligeng","year":"2020","unstructured":"Ligeng Chen, Zhongling He, and Bing Mao. 2020. Cati: Context-assisted type inference from stripped binaries. In 2020 50th Annual IEEE\/IFIP International Conference on Dependable Systems and Networks (DSN). IEEE, 88\u201398."},{"key":"e_1_3_1_34_2","unstructured":"Qibin Chen Jeremy Lacomis Edward J Schwartz Claire Le Goues Graham Neubig and Bogdan Vasilescu. 2022. Augmenting decompiler output with learned variable names and types. In USENIX Security."},{"key":"e_1_3_1_35_2","doi-asserted-by":"crossref","first-page":"677","DOI":"10.1109\/SP40001.2021.00114","volume-title":"2021 IEEE Symposium on Security and Privacy (SP)","author":"Choi Jaeseung","year":"2021","unstructured":"Jaeseung Choi, Kangsu Kim, Daejin Lee, and Sang Kil Cha. 2021. NTFuzz: Enabling type-aware kernel fuzzing on windows with static binary analysis. In 2021 IEEE Symposium on Security and Privacy (SP). IEEE, 677\u2013693."},{"key":"e_1_3_1_36_2","volume-title":"Reverse compilation techniques.","author":"Cifuentes Cristina","year":"1994","unstructured":"Cristina Cifuentes. 1994. Reverse compilation techniques. Queensland University of Technology, Brisbane."},{"issue":"7","key":"e_1_3_1_37_2","article-title":"Decompilation of Binary Programs.","volume":"25","author":"Cifuentes Cristina","year":"1995","unstructured":"Cristina Cifuentes and K. John Gough. 1995. Decompilation of Binary Programs. Softw. Pract. Exper. 25, 7 (July 1995).","journal-title":"Softw. Pract. Exper."},{"key":"e_1_3_1_38_2","doi-asserted-by":"crossref","unstructured":"Sandeep Dasgupta Sushant Dinesh Deepan Venkatesh Vikram S Adve and Christopher W Fletcher. 2020. Scalable Validation for Binary Lifters.","DOI":"10.1145\/3385412.3385964"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3428293"},{"key":"e_1_3_1_40_2","doi-asserted-by":"crossref","unstructured":"Yaniv David Nimrod Partush and Eran Yahav. 2018. FirmUp: Precise Static Detection of Common Vulnerabilities in Firmware. In ASPLOS.","DOI":"10.1145\/3173162.3177157"},{"key":"e_1_3_1_41_2","doi-asserted-by":"crossref","unstructured":"Yaniv David and Eran Yahav. 2014. Tracelet-based Code Search in Executables. In PLDI.","DOI":"10.1145\/2594291.2594343"},{"key":"e_1_3_1_42_2","doi-asserted-by":"crossref","unstructured":"Chinmay Deshpande Fabian Parzefall Felicitas Hetzelt and Michael Franz. 2024. Polynima: Practical Hybrid Recompilation for Multithreaded Binaries. In Proceedings of the Nineteenth European Conference on Computer Systems.","DOI":"10.1145\/3627703.3650065"},{"key":"e_1_3_1_43_2","doi-asserted-by":"crossref","first-page":"1497","DOI":"10.1109\/SP40000.2020.00009","volume-title":"2020 IEEE Symposium on Security and Privacy (SP)","author":"Dinesh Sushant","year":"2020","unstructured":"Sushant Dinesh, Nathan Burow, Dongyan Xu, and Mathias Payer. 2020. Retrowrite: Statically instrumenting cots binaries for fuzzing and sanitization. In 2020 IEEE Symposium on Security and Privacy (SP). IEEE, 1497\u20131511."},{"key":"e_1_3_1_44_2","unstructured":"Yangruibo Ding Benjamin Steenhoek Kexin Pei Gail Kaiser Wei Le and Baishakhi Ray. 2024. Traced: Execution-aware pre-training for source code. In Proceedings of the 46th IEEE\/ACM International Conference on Software Engineering."},{"key":"e_1_3_1_45_2","doi-asserted-by":"crossref","unstructured":"Gregory J Duck Xiang Gao and Abhik Roychoudhury. 2020. Binary rewriting without control flow recovery. In Proceedings of the 41st ACM SIGPLAN conference on programming language design and implementation. 151\u2013163.","DOI":"10.1145\/3385412.3385972"},{"key":"e_1_3_1_46_2","doi-asserted-by":"crossref","unstructured":"Khaled ElWazeer Kapil Anand Aparna Kotha Matthew Smithson and Rajeev Barua. 2013. Scalable Variable and Data Type Detection in a Binary Rewriter. In PLDI.","DOI":"10.1145\/2491956.2462165"},{"key":"e_1_3_1_47_2","doi-asserted-by":"crossref","unstructured":"Han Gao Shaoyin Cheng Yinxing Xue and Weiming Zhang. 2021. A lightweight framework for function name reassignment based on large-scale stripped binaries. In ISSTA.","DOI":"10.1145\/3460319.3464804"},{"issue":"11","key":"e_1_3_1_48_2","article-title":"Shortcut learning in deep neural networks.","volume":"2","author":"Geirhos Robert","year":"2020","unstructured":"Robert Geirhos, J\u00f6rn-Henrik Jacobsen, Claudio Michaelis, Richard Zemel, Wieland Brendel, Matthias Bethge, and Felix A Wichmann. 2020. Shortcut learning in deep neural networks. Nature Machine Intelligence 2, 11 (2020).","journal-title":"Nature Machine Intelligence"},{"key":"e_1_3_1_49_2","unstructured":"Daya Guo Qihao Zhu Dejian Yang Zhenda Xie Kai Dong Wentao Zhang Guanting Chen Xiao Bi Yu Wu YK Li et al.. 2024. DeepSeek-Coder: When the Large Language Model Meets Programming\u2013The Rise of Code Intelligence. arXiv preprint arXiv:2401.14196 (2024)."},{"key":"e_1_3_1_50_2","unstructured":"Keerthana Gurushankar and Pulkit Grover. 2021. A minimal intervention definition of reverse engineering a neural circuit. arXiv preprint arXiv:2110.00889 (2021)."},{"issue":"12","key":"e_1_3_1_51_2","doi-asserted-by":"crossref","first-page":"782","DOI":"10.1145\/365691.365943","article-title":"Machine independence: its technology and economics.","volume":"8","author":"Halpern Mark I","year":"1965","unstructured":"Mark I Halpern. 1965. Machine independence: its technology and economics. Commun. ACM 8, 12 (1965), 782\u2013785.","journal-title":"Commun. ACM"},{"key":"e_1_3_1_52_2","volume-title":"2023 IEEE Symposium on Security and Privacy (SP)","author":"Han HyungSeok","year":"2023","unstructured":"HyungSeok Han, JeongOh Kyea, Yonghwi Jin, Jinoh Kang, Brian Pak, and Insu Yun. 2023. QueryX: Symbolic Query on Decompiled Code for Finding Bugs in COTS Binaries. In 2023 IEEE Symposium on Security and Privacy (SP). IEEE."},{"key":"e_1_3_1_53_2","unstructured":"Jingxuan He Pesho Ivanov Petar Tsankov Veselin Raychev and Martin Vechev. 2018. Debin: Predicting Debug Information in Stripped Binaries. In CCS \u201918."},{"key":"e_1_3_1_54_2","unstructured":"SA Hex-Rays. 2014. IDA Pro: a cross-platform multi-processor disassembler and debugger."},{"key":"e_1_3_1_55_2","unstructured":"Peiwei Hu Ruigang Liang and Kai Chen. 2024. DeGPT: Optimizing Decompiler Output with LLM. (2024)."},{"key":"e_1_3_1_56_2","unstructured":"Ziwei Ji Nayeon Lee Rita Frieske Tiezheng Yu Dan Su Yan Xu Etsuko Ishii Ye Jin Bang Andrea Madotto and Pascale Fung. 2023. Survey of Hallucination in Natural Language Generation. (2023)."},{"key":"e_1_3_1_57_2","unstructured":"Zhenlan Ji Pingchuan Ma Zongjie Li and Shuai Wang. 2023. Benchmarking and explaining large language modelbased code generation: A causality-centric approach. arXiv preprint arXiv:2310.06680 (2023)."},{"key":"e_1_3_1_58_2","unstructured":"Zhenlan Ji Daoyuan Wu Pingchuan Ma Zongjie Li and Shuai Wang. 2024. Testing and Understanding Erroneous Planning in LLM Agents through Synthesized User Inputs. arXiv preprint arXiv:2404.17833 (2024)."},{"key":"e_1_3_1_59_2","unstructured":"Nan Jiang Chengxiao Wang Kevin Liu Xiangzhe Xu Lin Tan and Xiangyu Zhang. 2024. Nova: Generative Language Models for Assembly Code with Hierarchical Attention and Contrastive Learning. arXiv:2311.13721 (2024)."},{"key":"e_1_3_1_60_2","doi-asserted-by":"crossref","unstructured":"Xin Jin Kexin Pei Jun Yeon Won and Zhiqiang Lin. 2022. Symlm: Predicting function names in stripped binaries via context-sensitive execution-aware code embeddings. In CCS.","DOI":"10.1145\/3548606.3560612"},{"key":"e_1_3_1_61_2","unstructured":"Jean Kaddour Joshua Harris Maximilian Mozes Herbie Bradley Roberta Raileanu and Robert McHardy. 2023. Challenges and applications of large language models. arXiv preprint arXiv:2307.10169 (2023)."},{"key":"e_1_3_1_62_2","unstructured":"Ping Fan Ke and Ka Chung Ng. 2025. Human-AI Synergy in Survey Development: Implications from Large Language Models in Business and Research. ACM Transactions on Management Information Systems (2025)."},{"key":"e_1_3_1_63_2","unstructured":"Sun Hyoung Kim Cong Sun Dongrui Zeng and Gang Tan. 2021. Refining Indirect Call Targets at the Binary Level.. In NDSS."},{"key":"e_1_3_1_64_2","doi-asserted-by":"crossref","unstructured":"Takeshi Kojima Shixiang Shane Gu Machel Reid Yutaka Matsuo and Yusuke Iwasawa. 2022. Large language models are zero-shot reasoners. Advances in neural information processing systems 35 (2022) 22199\u201322213.","DOI":"10.52202\/068431-1613"},{"key":"e_1_3_1_65_2","doi-asserted-by":"crossref","unstructured":"Jeremy Lacomis Pengcheng Yin Edward Schwartz Miltiadis Allamanis Claire Le Goues Graham Neubig and Bogdan Vasilescu. 2019. Dire: A neural approach to decompiled identifier naming. In ASE.","DOI":"10.1109\/ASE.2019.00064"},{"key":"e_1_3_1_66_2","unstructured":"Patrick Lewis Ethan Perez Aleksandra Piktus Fabian Petroni Vladimir Karpukhin Naman Goyal Heinrich K\u00fcttler Mike Lewis Wen-tau Yih Tim Rockt\u00e4schel et al.. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems 33 (2020) 9459\u20139474."},{"key":"e_1_3_1_67_2","doi-asserted-by":"crossref","unstructured":"Yujia Li David Choi Junyoung Chung Nate Kushman Julian Schrittwieser R\u00e9mi Leblond Tom Eccles James Keeling Felix Gimeno Agustin Dal Lago et al.. 2022. Competition-level code generation with alphacode. Science 378 (2022).","DOI":"10.1126\/science.abq1158"},{"key":"e_1_3_1_68_2","unstructured":"Zongjie Li Zhibo Liu Wai Kin Wong Pingchuan Ma and Shuai Wang. 2024. Evaluating C\/C++ Vulnerability Detectability of Query-Based Static Application Security Testing Tools. IEEE Transactions on Dependable and Secure Computing (2024)."},{"key":"e_1_3_1_69_2","unstructured":"Zongjie Li Pingchuan Ma Huaijin Wang Shuai Wang Qiyi Tang Sen Nie and Shi Wu. 2022. Unleashing the Power of Compiler Intermediate Representation to Enhance Neural Program Embeddings. In ICSE."},{"key":"e_1_3_1_70_2","unstructured":"Zongjie Li Chaozheng Wang Zhibo Liu Haoxuan Wang Dong Chen Shuai Wang and Cuiyun Gao. 2023. CCTEST: Testing and Repairing Code Completion Systems. In ICSE."},{"key":"e_1_3_1_71_2","unstructured":"Zongjie Li Chaozheng Wang Pingchuan Ma Daoyuan Wu Shuai Wang Cuiyun Gao and Yang Liu. 2024. Split and Merge: Aligning Position Biases in LLM-based Evaluators. In EMNLP."},{"key":"e_1_3_1_72_2","unstructured":"Zongjie Li Daoyuan Wu Shuai Wang and Zhendong Su. 2024. API-guided Dataset Synthesis to Finetune Large Code Models. arXiv preprint arXiv:2408.08343 (2024)."},{"key":"e_1_3_1_73_2","unstructured":"Nelson F Liu Kevin Lin John Hewitt Ashwin Paranjape Michele Bevilacqua Fabian Petroni and Percy Liang. 2023. Lost in the middle: How language models use long contexts. arXiv preprint arXiv:2307.03172 (2023)."},{"key":"e_1_3_1_74_2","doi-asserted-by":"crossref","unstructured":"Yuwei Liu Siqi Chen Yuchong Xie Yanhao Wang Libo Chen Bin Wang Yingming Zeng Zhi Xue and Purui Su. 2023. VD-Guard: DMA Guided Fuzzing for Hypervisor Virtual Device. In ASE.","DOI":"10.1109\/ASE56229.2023.00051"},{"key":"e_1_3_1_75_2","doi-asserted-by":"crossref","unstructured":"Ye Liu Yue Xue Daoyuan Wu Yuqiang Sun Yi Li Miaolei Shi and Yang Liu. 2025. Propertygpt: Llm-driven formal verification of smart contracts through retrieval-augmented property generation. In NDSS.","DOI":"10.14722\/ndss.2025.241357"},{"key":"e_1_3_1_76_2","doi-asserted-by":"crossref","unstructured":"Zhibo Liu and Shuai Wang. 2020. How far we have come: testing decompilation correctness of C decompilers. Proceedings of the 29th ACM SIGSOFT International Symposium on Software Testing and Analysis (2020).","DOI":"10.1145\/3395363.3397370"},{"key":"e_1_3_1_77_2","first-page":"1100","volume-title":"2022 IEEE Symposium on Security and Privacy (SP)","author":"Liu Zhibo","year":"2022","unstructured":"Zhibo Liu, Yuanyuan Yuan, Shuai Wang, and Yuyan Bao. 2022. Sok: Demystifying binary lifters through the lens of downstream applications. In 2022 IEEE Symposium on Security and Privacy (SP). IEEE, 1100\u20131119."},{"key":"e_1_3_1_78_2","unstructured":"Zhibo Liu Yuanyuan Yuan Shuai Wang Xiaofei Xie and Lei Ma. 2023. Decompiling x86 deep neural network executables. In 32nd USENIX Security Symposium (USENIX Security 23). 7357\u20137374."},{"issue":"6","key":"e_1_3_1_79_2","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1145\/1064978.1065034","article-title":"Pin: building customized program analysis tools with dynamic instrumentation.","volume":"40","author":"Luk Chi-Keung","year":"2005","unstructured":"Chi-Keung Luk, Robert Cohn, Robert Muth, Harish Patil, Artur Klauser, Geoff Lowney, Steven Wallace, Vijay Janapa Reddi, and Kim Hazelwood. 2005. Pin: building customized program analysis tools with dynamic instrumentation. Acm sigplan notices 40, 6 (2005), 190\u2013200.","journal-title":"Acm sigplan notices"},{"key":"e_1_3_1_80_2","doi-asserted-by":"crossref","unstructured":"Alessandro Mantovani Luca Compagna Yan Shoshitaishvili and Davide Balzarotti. 2022. The Convergence of Source Code and Binary Vulnerability Discovery\u2013A Case Study (AsiaCCS).","DOI":"10.1145\/3488932.3497764"},{"key":"e_1_3_1_81_2","doi-asserted-by":"crossref","unstructured":"Kenneth Miller Yonghwi Kwon Yi Sun Zhuo Zhang Xiangyu Zhang and Zhiqiang Lin. 2019. Probabilistic Disassembly. In ICSE.","DOI":"10.1109\/ICSE.2019.00121"},{"key":"e_1_3_1_82_2","unstructured":"Stefan Nagy Anh Nguyen-Tuong Jason D Hiser Jack W Davidson and Matthew Hicks. 2021. Breaking through binaries: Compiler-quality instrumentation for better binary-only fuzzing. In USENIX Security 21."},{"issue":"6","key":"e_1_3_1_83_2","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1145\/1273442.1250746","article-title":"Valgrind: a framework for heavyweight dynamic binary instrumentation.","volume":"42","author":"Nethercote Nicholas","year":"2007","unstructured":"Nicholas Nethercote and Julian Seward. 2007. Valgrind: a framework for heavyweight dynamic binary instrumentation. ACM Sigplan notices 42, 6 (2007), 89\u2013100.","journal-title":"ACM Sigplan notices"},{"key":"e_1_3_1_84_2","unstructured":"Lily Hay Newman. 2019. The NSA makes Ghidra a powerful cybersecurity tool open source. https:\/\/www.wired.com\/story\/nsa-ghidra-open-source-tool\/."},{"key":"e_1_3_1_85_2","unstructured":"nist. 2021. Juliet Test Suite for C\/C++. https:\/\/samate.nist.gov\/SRD\/testsuite.php."},{"key":"e_1_3_1_86_2","unstructured":"National Security Agency (NSA). 2018. Ghidra. https:\/\/www.nsa.gov\/resources\/everyone\/ghidra\/."},{"key":"e_1_3_1_87_2","unstructured":"OpenAI. 2023. GPT-4 Technical Report. ArXiv abs\/2303.08774 (2023)."},{"key":"e_1_3_1_88_2","doi-asserted-by":"crossref","unstructured":"Long Ouyang Jeffrey Wu Xu Jiang Diogo Almeida Carroll Wainwright Pamela Mishkin Chong Zhang Sandhini Agarwal Katarina Slama Alex Ray et al.. 2022. Training language models to follow instructions with human feedback. Advances in neural information processing systems 35 (2022) 27730\u201327744.","DOI":"10.52202\/068431-2011"},{"key":"e_1_3_1_89_2","unstructured":"Kuntal Kumar Pal Ati Priya Bajaj Pratyay Banerjee Audrey Dutcher Mutsumi Nakamura Zion Leonahenahe Basque Himanshu Gupta Saurabh Arjun Sawant Ujjwala Anantheswaran Yan Shoshitaishvili et al.. 2024. len or index or count anything but v1\u201d: Predicting variable names in decompilation output with transfer learning. In IEEE S&P."},{"key":"e_1_3_1_90_2","doi-asserted-by":"crossref","unstructured":"Chengbin Pang Ruotong Yu Yaohui Chen Eric Koskinen Georgios Portokalidis Bing Mao and Jun Xu. 2021. Sok: All you ever wanted to know about x86\/x64 binary disassembly but were afraid to ask. In IEEE S&P.","DOI":"10.1109\/SP40001.2021.00012"},{"key":"e_1_3_1_91_2","unstructured":"Chengbin Pang Tiantai Zhang Ruotong Yu Bing Mao and Jun Xu. 2022. Ground truth for binary disassembly is not easy. In 31st USENIX Security Symposium (USENIX Security 22). 2479\u20132495."},{"key":"e_1_3_1_92_2","doi-asserted-by":"crossref","unstructured":"Fabian Parzefall Chinmay Deshpande Felicitas Hetzelt and Michael Franz. 2024. What you trace is what you get: dynamic stack-layout recovery for binary recompilation. In ASPLOS.","DOI":"10.1145\/3620665.3640371"},{"key":"e_1_3_1_93_2","doi-asserted-by":"crossref","unstructured":"Hammond Pearce Benjamin Tan Baleegh Ahmad Ramesh Karri and Brendan Dolan-Gavitt. 2023. Examining zero-shot vulnerability repair with large language models. In 2023 IEEE Symposium on Security and Privacy (SP). IEEE.","DOI":"10.1109\/SP46215.2023.10179324"},{"key":"e_1_3_1_94_2","doi-asserted-by":"crossref","unstructured":"Kexin Pei Jonas Guan Matthew Broughton Zhongtian Chen Songchen Yao David Williams-King Vikas Ummadisetty Junfeng Yang Baishakhi Ray and Suman Jana. 2021. StateFormer: Fine-grained type recovery from binaries using generative state modeling. In FSE\u201921. 690\u2013702.","DOI":"10.1145\/3468264.3468607"},{"key":"e_1_3_1_95_2","doi-asserted-by":"crossref","unstructured":"Yi Qian Ligeng Chen Yuyang Wang and Bing Mao. 2022. Nimbus: Toward speed up function signature recovery via input resizing and multi-task learning. In IEEE QRS.","DOI":"10.1109\/QRS57517.2022.00053"},{"key":"e_1_3_1_96_2","unstructured":"Pemma Reiter Hui Jun Tay Westley Weimer Adam Doup\u00e8 Ruoyu Wang and Stephanie Forrest. 2022. Automatically Mitigating Vulnerabilities in x86 Binary Programs via Partially Recompilable Decompilation. arXiv:2202.12336 (2022)."},{"issue":"2","key":"e_1_3_1_97_2","doi-asserted-by":"crossref","first-page":"358","DOI":"10.1090\/S0002-9947-1953-0053041-6","article-title":"Classes of recursively enumerable sets and their decision problems.","volume":"74","author":"Rice Henry Gordon","year":"1953","unstructured":"Henry Gordon Rice. 1953. Classes of recursively enumerable sets and their decision problems. Transactions of the American Mathematical society 74, 2 (1953), 358\u2013366.","journal-title":"Transactions of the American Mathematical society"},{"key":"e_1_3_1_98_2","unstructured":"Baptiste Rozi\u00e8re Jonas Gehring Fabian Gloeckle Sten Sootla Itai Gat Xiaoqing Ellen Tan Yossi Adi Jingyu Liu Tal Remez J\u00e9r\u00e9my Rapin et al.. 2023. Code llama: Open foundation models for code. arXiv:2308.12950 (2023)."},{"key":"e_1_3_1_99_2","unstructured":"Konstantin Serebryany Derek Bruening Alexander Potapenko and Dmitry Vyukov. 2012. AddressSanitizer: A Fast Address Sanity Checker (USENIX ATC\u201912). 28\u201328."},{"key":"e_1_3_1_100_2","unstructured":"Dongdong She Adam Storek Yuchong Xie Seoyoung Kweon Prashast Srivastava and Suman Jana. 2024. Fox: Coverage-guided fuzzing as online stochastic control. In CCS."},{"key":"e_1_3_1_101_2","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."},{"key":"e_1_3_1_102_2","unstructured":"Yuqiang Sun Daoyuan Wu Yue Xue Han Liu Haijun Wang Zhengzi Xu Xiaofei Xie and Yang Liu. 2024. Gptscan: Detecting logic vulnerabilities in smart contracts by combining gpt with program analysis. In ICSE."},{"key":"e_1_3_1_103_2","unstructured":"Hanzhuo Tan Qi Luo Jing Li and Yuqun Zhang. 2024. LLM4Decompile: Decompiling Binary Code with Large Language Models. arXiv preprint arXiv:2403.05286 (2024)."},{"key":"e_1_3_1_104_2","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al.. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_1_105_2","doi-asserted-by":"crossref","unstructured":"Huaijin Wang Zhibo Liu Yanbo Dai Shuai Wang Qiyi Tang Sen Nie and Shi Wu. 2025. Preserving Privacy in Software Composition Analysis: A Study of Technical Solutions and Enhancements. In ICSE.","DOI":"10.1109\/ICSE55347.2025.00055"},{"key":"e_1_3_1_106_2","doi-asserted-by":"crossref","unstructured":"Huaijin Wang Zhibo Liu Shuai Wang Ying Wang Qiyi Tang Sen Nie and Shi Wu. 2024. Are We There Yet? Filling the Gap Between Binary Similarity Analysis and Binary Software Composition Analysis. In IEEE EuroS&P\u201924.","DOI":"10.1109\/EuroSP60621.2024.00034"},{"key":"e_1_3_1_107_2","unstructured":"Huaijin Wang Pingchuan Ma Shuai Wang Qiyi Tang Sen Nie and Shi Wu. 2023. sem2vec: Semantics-aware assembly tracelet embedding. ACM Transactions on Software Engineering and Methodology (2023)."},{"key":"e_1_3_1_108_2","unstructured":"Huaijin Wang Pingchuan Ma Yuanyuan Yuan Zhibo Liu Shuai Wang Qiyi Tang Sen Nie and Shi Wu. 2022. Enhancing dnn-based binary code function search with low-cost equivalence checking. IEEE TSE (2022)."},{"key":"e_1_3_1_109_2","unstructured":"Huaijin Wang Shuai Wang Dongpeng Xu Xiangyu Zhang and Xiao Liu. 2020. Generating effective software obfuscation sequences with reinforcement learning. IEEE Transactions on Dependable and Secure Computing (2020)."},{"key":"e_1_3_1_110_2","unstructured":"Jinghan Wang Yue Duan Wei Song Heng Yin and Chengyu Song. 2019. Be sensitive and collaborative: Analyzing impact of coverage metrics in greybox fuzzing. In RAID 2019. 1\u201315."},{"key":"e_1_3_1_111_2","doi-asserted-by":"crossref","unstructured":"Pei Wang Qinkun Bao Li Wang Shuai Wang Zhaofeng Chen Tao Wei and Dinghao Wu. 2018. Software Protection on the Go: A Large-scale Empirical Study on Mobile App Obfuscation. In ICSE.","DOI":"10.1145\/3180155.3180169"},{"key":"e_1_3_1_112_2","doi-asserted-by":"crossref","unstructured":"Ruoyu Wang Yan Shoshitaishvili Antonio Bianchi Aravind Machiry John Grosen Paul Grosen Christopher Kruegel and Giovanni Vigna. 2017. Ramblr: Making Reassembly Great Again.. In NDSS.","DOI":"10.14722\/ndss.2017.23225"},{"key":"e_1_3_1_113_2","unstructured":"Shuai Wang Pei Wang and Dinghao Wu. 2015. Reassembleable disassembling. In 24th USENIX Security Symposium (USENIX Security 15). 627\u2013642."},{"key":"e_1_3_1_114_2","doi-asserted-by":"crossref","unstructured":"David Williams-King Hidenori Kobayashi Kent Williams-King Graham Patterson Frank Spano Yu Jian Wu Junfeng Yang and Vasileios P Kemerlis. 2020. Egalito: Layout-agnostic binary recompilation. In ASPLOS.","DOI":"10.1145\/3373376.3378470"},{"key":"e_1_3_1_115_2","doi-asserted-by":"crossref","unstructured":"Wai Kin Wong Huaijin Wang Zongjie Li and Shuai Wang. 2024. Binaug: Enhancing binary similarity analysis with low-cost input repairing. In Proceedings of the 46th IEEE\/ACM International Conference on Software Engineering.","DOI":"10.1145\/3597503.3623328"},{"key":"e_1_3_1_116_2","doi-asserted-by":"crossref","unstructured":"Wai Kin Wong Huaijin Wang Pingchuan Ma Shuai Wang Mingyue Jiang Tsong Yueh Chen Qiyi Tang Sen Nie and Shi Wu. 2022. Deceiving Deep Neural Networks-Based Binary Code Matching with Adversarial Programs. In 2022 IEEE International Conference on Software Maintenance and Evolution (ICSME).","DOI":"10.1109\/ICSME55016.2022.00019"},{"key":"e_1_3_1_117_2","unstructured":"Xuansheng Wu Wenlin Yao Jianshu Chen Xiaoman Pan Xiaoyang Wang Ninghao Liu and Dong Yu. 2024. From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning. NAACL (2024)."},{"key":"e_1_3_1_118_2","unstructured":"Shusheng Xu Wei Fu Jiaxuan Gao Wenjie Ye Weilin Liu Zhiyu Mei Guangju Wang Chao Yu and Yi Wu. 2024. Is dpo superior to ppo for llm alignment? a comprehensive study. arXiv preprint arXiv:2404.10719 (2024)."},{"key":"e_1_3_1_119_2","unstructured":"Xiangzhe Xu Zhuo Zhang Shiwei Feng Yapeng Ye Zian Su Nan Jiang Siyuan Cheng Lin Tan and Xiangyu Zhang. 2023. LmPa: Improving Decompilation by Synergy of Large Language Model and Program Analysis. arXiv preprint arXiv:2306.02546 (2023)."},{"key":"e_1_3_1_120_2","unstructured":"Xiangzhong Yu Wai Kin Wong and Shuai Wang. 2024. EMI Testing of Large Language Model (LLM) Compilers. In 2024 IEEE 35th International Symposium on Software Reliability Engineering Workshops (ISSREW)."},{"key":"e_1_3_1_121_2","doi-asserted-by":"crossref","unstructured":"Andreas Zeller. 2005. Why Programs Fail: A Guide to Systematic Debugging. Morgan Kaufmann Publishers Inc.","DOI":"10.1016\/B978-155860866-5\/50008-4"},{"key":"e_1_3_1_122_2","unstructured":"Kunpeng Zhang Zongjie Li Daoyuan Wu Shuai Wang and Xin Xia. 2025. Low-Cost and Comprehensive Non-textual Input Fuzzing with LLM-Synthesized Input Generators. In 34rd USENIX Security Symposium (USENIX Security 25)."},{"key":"e_1_3_1_123_2","doi-asserted-by":"crossref","unstructured":"Zhuo Zhang Yapeng Ye Wei You Guanhong Tao Wen-chuan Lee Yonghwi Kwon Yousra Aafer and Xiangyu Zhang. 2021. Osprey: Recovery of variable and data structure via probabilistic analysis for stripped binary. In IEEE S&P.","DOI":"10.1109\/SP40001.2021.00051"},{"key":"e_1_3_1_124_2","unstructured":"Anshunkang Zhou Chengfeng Ye Heqing Huang Yuandao Cai and Charles Zhang. 2024. Plankton: Reconciling Binary Code and Debug Information. In ASPLOS."}],"container-title":["Proceedings of the ACM on Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3728958","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T13:47:18Z","timestamp":1787492838000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3728958"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":124,"journal-issue":{"issue":"ISSTA","published-print":{"date-parts":[[2025,6,22]]}},"alternative-id":["10.1145\/3728958"],"URL":"https:\/\/doi.org\/10.1145\/3728958","relation":{},"ISSN":["2994-970X"],"issn-type":[{"value":"2994-970X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,22]]}}}