自适应和稳健的成本感知质量证明用于去中心化大语言模型推理网络
Adaptive and Robust Cost-Aware Proof of Quality for Decentralized LLM Inference Networks
AI总结：
本文提出一种自适应和稳健的成本感知质量证明机制，通过鲁棒聚合规则和动态信任权重提升共识一致性，减少对抗攻击影响。
摘要：
去中心化的大型语言模型推理网络需要轻量级机制来在异构延迟和成本下奖励高质量输出。Proof of Quality通过采样评估节点对候选输出进行评分，然后将评分汇总成共识信号以确定奖励。然而，评估者异质性和恶意评分操纵可能会扭曲共识并增加付款额，这会削弱开放参与环境中的激励对齐。本文通过添加对抗鲁棒的共识形成机制扩展了成本感知的Proof of Quality机制。我们研究了鲁棒聚合规则，包括中位数和修剪均值，以及一种自适应信任加权共识，该共识通过偏差信号更新评估者的权重。使用问答和摘要工作负载，并通过地面真实代理进行离线分析，我们量化了评估者的可靠性，并展示了评估者之间显著的方差，包括任务依赖性的不一致，这可以反转相关性。然后，我们在四种对抗策略下评估鲁棒性，包括噪声注入、增强、破坏和间歇性操纵，涵盖恶意比例和评估者样本大小的广泛范围。我们的结果表明，鲁棒聚合提高了与地面真实代理的一致性，并且相比简单的平均，减少了对噪声和战略攻击的敏感性。我们进一步刻画了由评估者采样引入的操作权衡，其中更大的评估者集合会减少评估者奖励并增加收益方差，而推理奖励在我们的配置中相对稳定。这些发现促使鲁棒共识成为成本感知Proof of Quality的默认组件，并为在对抗风险和资源约束下选择评估者采样参数提供了实用指导。
英文摘要：
Decentralized large language model inference networks require lightweight mechanisms to reward high quality outputs under heterogeneous latency and cost. Proof of Quality provides scalable verification by sampling evaluator nodes that score candidate outputs, then aggregating their scores into a consensus signal that determines rewards. However, evaluator heterogeneity and malicious score manipulation can distort consensus and inflate payouts, which weakens incentive alignment in open participation settings. This paper extends a cost-aware Proof of Quality mechanism by adding adversary-resilient consensus formation. We study robust aggregation rules, including median and trimmed mean, and an adaptive trust-weighted consensus that updates evaluator weights from deviation signals. Using question answering and summarization workloads with a ground truth proxy for offline analysis, we quantify evaluator reliability and show strong variance across evaluators, including task-dependent misalignment that can invert correlations. We then evaluate robustness under four adversarial strategies, including noise injection, boosting, sabotage, and intermittent manipulation, across a sweep of malicious ratios and evaluator sample sizes. Our results show that robust aggregation improves consensus alignment with the ground truth proxy and reduces sensitivity to noisy and strategic attacks compared with simple averaging. We further characterize the operational trade-off introduced by evaluator sampling, where larger evaluator sets reduce evaluator rewards and increase payoff variance while inference rewards remain relatively stable in our configuration. These findings motivate robust consensus as a default component for cost-aware Proof of Quality and provide practical guidance for selecting evaluator sampling parameters under adversarial risk and resource constraints.
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。
