Many Repairs, One Direction: Steering Code Models Toward Safer Cryptographic API Use

Tianhe Lu, Sakuna Harinda Jayasundara, Eric Spero, Ewan Tempero, Robert Biddle, Giovanni Russello · 2026 · arXiv

DOI: 10.48550/arXiv.2610.25133 · open-access PDF

Portuguese

Enquanto muitas abordagens existentes melhoram a segurança do código modificando parâmetros do modelo ou entradas, como as mudanças de representação associadas a diferentes reparos de API criptográficos podem suportar uma intervenção compartilhada para geração de código mais segura permanece inexplorada. Para investigar isso, construímos 48.000 pares de programas correspondentes em quatro idiomas de programação e dez categorias de abuso de API criptográficos.

Machine translation (Meta M2M100); the English original follows.

Abstract

Cryptographic API misuse in large language model-generated code can compromise software security. While many existing approaches improve code security by modifying model parameters or inputs, how representation changes associated with different cryptographic API repairs can support a shared intervention for safer code generation remains underexplored. To investigate this, we construct 48,000 matched program pairs across four programming languages and ten cryptographic API misuse categories. Each pair changes a specified API decision while preserving the programming task. Subtracting the misuse

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.25133, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange