“人工智能黑客”的法律规制

Legal regulation of“artificial intelligence hacker”

从历史上看,“黑客”迭代到“人工智能黑客”,是伴随着计算机、互联网、大数据和人工智能等科学技术迅猛发展而产生的。现如今的“人工智能黑客”是人机交互体,既非人也非物,介于两者之间,它可以模仿人类、干扰人类认知,为达到设计者或决策者的目的对网络系统漏洞进行智能化侵入和破坏。“人工智能黑客”区别于传统“黑客”的主要特征在于其可以依靠智能算法自主学习、寻找网络系统代码漏洞和加强分布式攻击。部分学者将人工智能技术划分为弱人工智能、强人工智能、超人工智能三个阶段,甚至有学者建议从伦理上赋予强人工智能法律主体地位,赋权理由是强人工智能算法具有独立的“机器意思”表示能力,与人类有情感的联结。显然,这种赋权方式不仅违背“人本主义”原则的主体创新,而且现行法律主体包括自然人、法人、非法人组织,“人工智能黑客”不属于任何一类主体,突兀地将法律主体的理性意思表示与人工智能算法指令的“机器意思”相等同,容易形成“人工智能黑客”行为在算法正义法律评价和民事法律行为构造上的困境,干扰我们对“人工智能黑客”本质的判断。溯本清源,应当以法律上权利义务构造标准去判断“人工智能黑客”的法律属性。“人工智能黑客”本质上是自然人主体通过人工智能算法技术,利用网络媒介进行网络侵权或犯罪的行为。“人工智能黑客”的核心是通过计算机代码设置、大数据运算与机器自动化判断进行决策的一套机制。“人工智能黑客”在责任承担上不是适格的法律主体,只具有特殊的“人格性工具”法律属性。“人工智能黑客”的智能化攻击外在表现为算法程序的自动执行,但程序的设计和算法运行归属于现实经济生活中的人,也完全符合法律上间接侵权的调整范畴。对于“人工智能黑客”的侵权或犯罪行为,应当通过揭开“人工智能黑客”的“面纱”,找到其背后隐藏的可规制法律主客体,利用“穿透”方式对“人工智能黑客”的非法行为进行伦理、技术和法律三个维度的有效规制。

Historically,the iteration of“hacker”to“artificial intelligence hacker”was accompanied by the rapid development of science and technology,such as computer,internet,big data and artificial intelligence.Nowadays,“artificial intelligence hacker”is a human-computer interaction,which is neither a person nor a thing.It can imitate human beings,interfere with human cognition,and intelligently invade and destroy network system vulnerabilities for the purpose of designers or decision makers.The main feature of“artificial intelligence hacker”is that it can rely on intelligent algorithms to learn autonomously,find network system code vulnerabilities and strengthen distributed attacks.Some scholars divide artificial intelligence technology into three stages:weak artificial intelligence,strong artificial intelligence and super artificial intelligence.Some scholars even suggest that strong artificial intelligence be given the legal subject status ethically,because strong artificial intelligence algorithm has independent“machine meaning”expression ability and has emotional connection with human beings.Obviously,this way of empowerment violates the principle of“humanism”.Also,the current legal subject includes natural person,legal person,unincorporated organization,“artificial intelligence hacker”does not belong to any kind of subject,abruptly equating the rational expression of legal subjects with the“machine meaning”of artificial intelligence algorithm instructions can easily lead to difficulties in algorithmic justice legal evaluation and civil legal behavior construction of“artificial intelligence hacker”behavior,interfering with our judgment on the nature of“artificial intelligence hacker”.The legal attribute of“artificial intelligence hacker”should be judged based on legal rights and obligations.In essence,“artificial intelligence hacker”is a natural person who uses network media to commit network infringement or crime through artificial intelligence algorithm technology.The core of“artificial intelligence hacker”is a set of mechanism for making decisions through computer code setting,big data operation and automatic judgment of machines.“Artificial intelligence hacker”is not a proper legal subject in terms of responsibility,but has a special legal attribute of“personality tool”.The intelligent attack of“artificial intelligence hacker”is manifested by the automatic execution of the algorithm program,but the design and operation of the program belong to people in real economic life,which also fully conforms to the adjustment scope of indirect infringement in law.For criminal acts or infringement of“artificial intelligence hackers”,the hidden subject and object can be regulated by law should be found through piercing the“veil”of“artificial intelligence hacker”,and the“penetration”method should be used for the effective regulation of illegal behaviors of“artificial intelligence hackers”from the dimensions of ethics,technology and law.