Defending AI based FinTech Systems against Model Extraction Attacks

保护基于人工智能的金融科技系统免受模型提取攻击

• 批准号: LP200200084
• 负责人: A/Prof Sheng Wen
• 金额: $ 28.69万
• 依托单位: Swinburne University of Technology
• 依托单位国家: 澳大利亚
• 项目类别: Linkage Projects
• 财政年份: 2021
• 资助国家: 澳大利亚
• 起止时间: 2021-10-15 至 2024-10-14
• 项目状态: 已结题
• 来源: https://dataportal.arc.gov.au/RGS/Web/Grants/LP200200084
• 关键词: Defending; AI; based; FinTech; Systems

This project aims to develop new methods for defending artificial intelligence (AI) based FinTech systems from highly potent and insidious model extraction attacks whereby an adversary can steal the AI model from the system to cause intellectual property (IP) violation, business advantage disruption, and financial loss. This can be achieved by examining various attack models, creating active and utility-preserving defences, and inventing non-removable watermarks on AI models. The outcomes are new tools for securing AI-based FinTech systems before deployment and tools for IP violation forensics post-deployment. Such capabilities are beneficial by improving the security and safety of FinTech systems and other nationally critical AI systems.

该项目旨在开发新方法，保护基于人工智能 (AI) 的金融科技系统免受强大且阴险的模型提取攻击，攻击者可以从系统中窃取人工智能模型，从而导致知识产权 (IP) 侵犯、业务优势破坏和财务损失。这可以通过检查各种攻击模型、创建主动且实用的防御以及在人工智能模型上发明不可移除的水印来实现。其成果是在部署前保护基于人工智能的金融科技系统的新工具以及在部署后进行知识产权侵权取证的工具。这些功能有利于提高金融科技系统和其他国家关键人工智能系统的安全性。