





















Abstract:Decentralized finance (DeFi) has introduced a new era of permissionless financial innovation but also led to unprecedented market manipulation. Without centralized oversight, malicious actors coordinate shilling campaigns and pump-and-dump schemes across various platforms. We propose a Multi-Agent Reinforcement Learning (MARL) framework for decentralized manipulation detection, modeling the interaction between manipulators and detectors as a dynamic adversarial game. This framework identifies suspicious patterns using delayed token price reactions as financial this http URL method introduces three innovations: (1) Group Relative Policy Optimization (GRPO) to enhance learning stability in sparse-reward and partially observable settings; (2) a theory-based reward function inspired by rational expectations and information asymmetry, differentiating price discovery from manipulation noise; and (3) a multi-modal agent pipeline that integrates LLM-based semantic features, social graph signals, and on-chain market data for informed this http URL framework is integrated within the Symphony system, a decentralized multi-agent architecture enabling peer-to-peer agent execution and trust-aware learning through distributed logs, supporting chain-verifiable evaluation. Symphony promotes adversarial co-evolution among strategic actors and maintains robust manipulation detection without centralized oracles, enabling real-time surveillance across global DeFi this http URL on 100,000 real-world discourse episodes and validated in adversarial simulations, Hide-and-Shill achieves top performance in detection accuracy and causal attribution. This work bridges multi-agent systems with financial surveillance, advancing a new paradigm for decentralized market intelligence. All resources are available at the Hide-and-Shill GitHub repository to promote open research and reproducibility.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2507.09179 [cs.AI] |
| (or arXiv:2507.09179v3 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2507.09179 arXiv-issued DOI via DataCite |
From: Ronghua Shi [view email]
[v1]
Sat, 12 Jul 2025 07:55:40 UTC (8,234 KB)
[v2]
Mon, 15 Sep 2025 16:44:40 UTC (8,234 KB)
[v3]
Sat, 23 May 2026 16:09:10 UTC (8,229 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理,仅供阅读参考。 原文来自 — 版权归原作者所有。