{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/efficient-avoidance-of-vulnerabilities-in","title":"Efficient Avoidance of Vulnerabilities in Auto-completed Smart Contract Code Using Vulnerability-constrained Decoding","arxiv_id":"2309.09826","date":"2023-09-18","proceeding":null,"authors":["André Storhaug","Jingyue Li","Tianyuan Hu"],"abstract":"Auto-completing code enables developers to speed up coding significantly. Recent advances in transformer-based large language model (LLM) technologies have been applied to code synthesis. However, studies show that many of such synthesized codes contain vulnerabilities. We propose a novel vulnerability-constrained decoding approach to reduce the amount of vulnerable code generated by such models. Using a small dataset of labeled vulnerable lines of code, we fine-tune an LLM to include vulnerability labels when generating code, acting as an embedded classifier. Then, during decoding, we deny the model to generate these labels to avoid generating vulnerable code. To evaluate the method, we chose to automatically complete Ethereum Blockchain smart contracts (SCs) as the case study due to the strict requirements of SC security. We first fine-tuned the 6-billion-parameter GPT-J model using 186,397 Ethereum SCs after removing the duplication from 2,217,692 SCs. The fine-tuning took more than one week using ten GPUs. The results showed that our fine-tuned model could synthesize SCs with an average BLEU (BiLingual Evaluation Understudy) score of 0.557. However, many codes in the auto-completed SCs were vulnerable. Using the code before the vulnerable line of 176 SCs containing different types of vulnerabilities to auto-complete the code, we found that more than 70% of the auto-completed codes were insecure. Thus, we further fine-tuned the model on other 941 vulnerable SCs containing the same types of vulnerabilities and applied vulnerability-constrained decoding. The fine-tuning took only one hour with four GPUs. We then auto-completed the 176 SCs again and found that our approach could identify 62% of the code to be generated as vulnerable and avoid generating 67% of them, indicating the approach could efficiently and effectively avoid vulnerabilities in the auto-completed code.","url_abs":"https://arxiv.org/abs/2309.09826v2","url_pdf":"https://arxiv.org/pdf/2309.09826v2.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":[],"tasks":[{"task_slug":"code-generation","task_name":"Code Generation"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"}],"methods":[{"method_slug":"vulnerability-constrained-decoding","method_name":"Vulnerability-constrained Decoding"}],"datasets_introduced":[{"slug":"verified-smart-contract-code-comments","name":"Verified Smart Contract Code Comments","full_name":""},{"slug":"verified-smart-contracts","name":"Verified Smart Contracts","full_name":""},{"slug":"vulnerable-verified-smart-contracts","name":"Vulnerable Verified Smart Contracts","full_name":""}],"methods_introduced":[{"slug":"vulnerability-constrained-decoding","name":"Vulnerability-constrained Decoding","full_name":"Vulnerability-constrained Decoding"}],"results":[{"leaderboard":"/sota/code-generation-on-verified-smart-contract","task":"Code Generation","dataset":"Verified Smart Contract Code Comments","model":"GPT-J 6B Smart Contract","rank_in_archive_order":1,"of":2,"metrics":{"BLEU score":"55.7"},"uses_additional_data":false},{"leaderboard":"/sota/code-generation-on-verified-smart-contract","task":"Code Generation","dataset":"Verified Smart Contract Code Comments","model":"GPT-J 6B","rank_in_archive_order":2,"of":2,"metrics":{"BLEU score":"25.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2309.09826","atlas_url":"https://app.syntology.ai/?focus=2309.09826","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2309.09826"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2309.09826\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2309.09826"},"call":"get_concepts_for_paper(arxiv_id=\"2309.09826\")"}],"by_repo":[],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"c753f6d087b15f4403f137963ed47e42829393d409fe06394b85655e93cab289","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}