当AI普及操纵:LLM辅助的公平分配算法战略操纵
When AI Democratizes Exploitation: LLM-Assisted Strategic Manipulation of Fair Division Algorithms
AI总结:
本文研究了LLM如何通过简化策略知识获取,使用户能操纵公平分配算法,揭示了协调偏好操纵在资源分配中的应用及影响。
摘要:
公平资源分配算法,如在Spliddit平台上实现的算法,传统上被认为难以被终端用户操纵,因为其复杂性。本文展示了大型语言模型(LLMs)如何通过普及战略专业知识的访问来打破这些保护屏障。通过在Spliddit算法上对租金分配场景的实证分析,我们展示了用户可以通过简单的对话查询给AI助手来获得可操作的操纵策略。我们提出了四个不同的操纵场景:排他性合谋,其中多数人利用少数人;防御性反制策略,这些策略反而失效;对特定参与者的善意补贴;以及成本最小化的联合体。我们的实验表明,LLMs能够解释算法机制,识别有利可图的偏差,并生成特定的数值输入用于协调的偏好误报——这些能力以前需要深入的技术知识。这些发现将算法集体行动理论从分类上下文扩展到资源分配场景,其中协调的偏好操纵取代了特征操纵。这些影响超越了租金分配,影响到任何使用算法公平机制进行资源分配的领域。虽然AI赋能的操纵对系统完整性构成风险,但也为公平群体创造了机会。我们主张有效的应对必须结合算法鲁棒性、参与式设计和公平获取AI能力,承认战略复杂性不再是稀缺资源。
英文摘要:
Fair resource division algorithms, like those implemented in Spliddit platform, have traditionally been considered difficult for the end users to manipulate due to its complexities. This paper demonstrates how Large Language Models (LLMs) can dismantle these protective barriers by democratizing access to strategic expertise. Through empirical analysis of rent division scenarios on Spliddit algorithms, we show that users can obtain actionable manipulation strategies via simple conversational queries to AI assistants. We present four distinct manipulation scenarios: exclusionary collusion where majorities exploit minorities, defensive counterstrategies that backfire, benevolent subsidization of specific participants, and cost minimization coalitions. Our experiments reveal that LLMs can explain algorithmic mechanics, identify profitable deviations, and generate specific numerical inputs for coordinated preference misreporting--capabilities previously requiring deep technical knowledge. These findings extend algorithmic collective action theory from classification contexts to resource allocation scenarios, where coordinated preference manipulation replaces feature manipulation. The implications reach beyond rent division to any domain using algorithmic fairness mechanisms for resource division. While AI-enabled manipulation poses risks to system integrity, it also creates opportunities for preferential treatment of equity deserving groups. We argue that effective responses must combine algorithmic robustness, participatory design, and equitable access to AI capabilities, acknowledging that strategic sophistication is no longer a scarce resource.
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。