{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/shellcode-ia32-a-dataset-for-automatic","title":"Shellcode_IA32: A Dataset for Automatic Shellcode Generation","arxiv_id":"2104.13100","date":"2021-04-27","proceeding":"ACL (NLP4Prog) 2021 8","authors":["Pietro Liguori","Erfan Al-Hossami","Domenico Cotroneo","Roberto Natella","Bojan Cukic","Samira Shaikh"],"abstract":"We take the first step to address the task of automatically generating shellcodes, i.e., small pieces of code used as a payload in the exploitation of a software vulnerability, starting from natural language comments. We assemble and release a novel dataset (Shellcode_IA32), consisting of challenging but common assembly instructions with their natural language descriptions. We experiment with standard methods in neural machine translation (NMT) to establish baseline performance levels on this task.","url_abs":"https://arxiv.org/abs/2104.13100v4","url_pdf":"https://arxiv.org/pdf/2104.13100v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"shellcode-ia32-a-dataset-for-automatic","repo_url":"https://github.com/dessertlab/Shellcode_IA32","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"code-generation","task_name":"Code Generation"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"bilstm","method_name":"BiLSTM"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"seq2seq","method_name":"Seq2Seq"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[{"slug":"shellcode-ia32","name":"Shellcode_IA32","full_name":"Shellcode_IA32"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/code-generation-on-shellcode-ia32","task":"Code Generation","dataset":"Shellcode_IA32","model":"LSTM-based Sequence to Sequence","rank_in_archive_order":3,"of":3,"metrics":{"BLEU-4":"62.97","Exact Match Accuracy":"51.55"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}