ManiScope: LLM-Assisted Visual Analytics of Cryptocurrency Manipulation Risk

2026-07-13

AI Summary

This study addresses the vulnerability of cryptocurrency markets to manipulative practices such as wash trading, a challenge exacerbated by existing risk assessment approaches that lack flexibility, interpretability, and efficient integration of multidimensional data. To overcome these limitations, this work proposes a synergistic system combining large language models (LLMs) with visual analytics. The system employs coordinated multi-view visualizations to reveal token distributions, holder relationships, price dynamics, and suspicious transaction patterns. Innovatively, the LLM acts as a co-analyst that actively interprets user hypotheses from interaction context and proactively surfaces multimodal evidence to support validation. Evaluation through a user study with twelve industry practitioners and two in-depth case studies demonstrates that the system substantially reduces manual evidence-gathering effort and effectively enables hypothesis-driven, structured risk assessment.

Abstract

Cryptocurrency markets are vulnerable to trade-based manipulation, such as wash trading, which can distort price signals and mislead investors. Prior research has mainly focused on detecting manipulation using fixed rules or labeled examples, offering limited flexibility and interpretability for assessing potential risks. Existing visual analytics tools can reveal basic manipulation-related signals, such as token distribution, but still require substantial manual effort to integrate holder relationships, suspicious behaviors, and market dynamics for risk assessment. To address these limitations, we propose ManiScope, an LLM-assisted visual analytics system for analyzing trade-based manipulation risks in cryptocurrency markets. ManiScope provides coordinated views of token distributions, holder relationships, detailed holder behaviors, price dynamics, and suspicious trading patterns. To further enhance user analysis, ManiScope introduces a human-LLM collaborative visual analytics framework. Rather than acting as a basic reactive LLM assistant, the framework positions the LLM as a co-analyst that infers users' analytical intent and emerging hypotheses from interaction context and surfaces relevant visual, statistical, and synthesized evidence for hypothesis evaluation. This design reduces repetitive inspection and strengthens evidence-based reasoning. We evaluate ManiScope through two case studies and a user study with 12 experienced cryptocurrency practitioners. The results suggest that ManiScope supports effective risk assessment of manipulation, reduces manual effort in evidence-seeking, and organizes findings around user hypotheses.

Problem

• cryptocurrency manipulation
• wash trading
• visual analytics
• manipulation risk
• holder relationships

Innovation

• LLM-assisted visual analytics
• cryptocurrency manipulation detection
• human-AI collaboration
• hypothesis-driven analysis
• interactive visualization