Attribution of Machine-generated Code for Accountability

机器生成代码的责任归属

• 批准号: DP240102164
• 负责人: Prof Yang Xiang
• 金额: $ 34.36万
• 依托单位: Swinburne University of Technology
• 依托单位国家: 澳大利亚
• 项目类别: Discovery Projects
• 财政年份: 2024
• 资助国家: 澳大利亚
• 起止时间: 2024-01-01 至 2026-12-31
• 项目状态: 未结题
• 来源: https://dataportal.arc.gov.au/RGS/Web/Grants/DP240102164
• 关键词: Attribution; Machine; generated; Code; Accountability; Attribution; Machine; generated; Code; Accountability

Machine-generated (or neural) code is usually produced by AI tools to speed up software development. However, such codes have recently raised serious security and privacy concerns. This project aims to attribute these codes to their generative models for accountability purposes. In the process, a series of new techniques are developed to differentiate between the codes generated by different models. The outcomes include analysis of neural code fingerprints, classification of neural codes, and theories to verify the correctness of code attribution. These will provide significant benefits, ranging from copyright protection to privacy preservation. This project is timely since currently the software community is pervasively using neural codes.

机器生成的（或神经）代码通常是由AI工具生成的，以加快软件开发。但是，这些代码最近引起了严重的安全和隐私问题。该项目的目的是将这些代码归因于其生成模型，以实现问责制。在此过程中，开发了一系列新技术来区分不同模型生成的代码。结果包括对神经代码指纹的分析，神经代码的分类以及验证代码归因的正确性的理论。这些将提供巨大的好处，从版权保护到隐私保护。该项目是及时的，因为当前软件社区使用神经代码普遍存在。