论人工智能开放性的考量:善意会被滥用吗?
On the Consideration of AI Openness: Can Good Intent Be Abused?
AI总结:
本文构建基于韩国刑事判例的 EVE-V1 与 EVE-V2 数据集,验证开源 LLM 微调后可提供犯罪建议,并分析相关法律责任与开源滥用风险。
摘要:
开源是科学进步背后的驱动力。然而,这种开放性也是一把双刃剑,其固有风险在于创新技术可能被滥用于对社会有害的目的。开源人工智能模型或数据集被用于实施现实世界犯罪的可能性有多大?如果犯罪分子确实利用了它,技术背后的人员能否逃脱法律责任?为了解决这些问题,我们探索了一个个人选择可能对社会产生重大影响的法律领域。具体而言,我们首先构建了 EVE-V1 数据集,该数据集包含基于 200 个韩国判例的 200 个与刑事犯罪相关的问答对,以探索恶意模型出现的可能性。我们进一步使用 600 个与欺诈相关的判例开发了 EVE-V2,以确认存在能够就广泛犯罪主题提供有害建议的恶意模型,从而测试领域泛化能力。值得注意的是,广泛使用的开源大规模语言模型(LLM)在使用 EVE 进行微调时,会提供关于犯罪活动的不道德且详细的信息。我们还深入审视了恶意语言模型及其构建者在现实中可能面临的法律问题。我们的研究结果凸显了一个矛盾困境:开源加速了科学进步,但需要高度谨慎以最大限度降低滥用可能性。警告:本文包含某些人可能认为不道德的内容。
英文摘要:
Open source is a driving force behind scientific advancement.However, this openness is also a double-edged sword, with the inherent risk that innovative technologies can be misused for purposes harmful to society. What is the likelihood that an open source AI model or dataset will be used to commit a real-world crime, and if a criminal does exploit it, will the people behind the technology be able to escape legal liability? To address these questions, we explore a legal domain where individual choices can have a significant impact on society. Specifically, we build the EVE-V1 dataset that comprises 200 question-answer pairs related to criminal offenses based on 200 Korean precedents first to explore the possibility of malicious models emerging. We further developed EVE-V2 using 600 fraud-related precedents to confirm the existence of malicious models that can provide harmful advice on a wide range of criminal topics to test the domain generalization ability. Remarkably, widely used open-source large-scale language models (LLMs) provide unethical and detailed information about criminal activities when fine-tuned with EVE. We also take an in-depth look at the legal issues that malicious language models and their builders could realistically face. Our findings highlight the paradoxical dilemma that open source accelerates scientific progress, but requires great care to minimize the potential for misuse. Warning: This paper contains content that some may find unethical.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。