Over $3.1 trillion in illicit money moves through the global financial system yearly, and much of it now uses stablecoins, which launderers prefer for their liquidity. Decentralized protocols increasingly hide transaction patterns with zero-knowledge proofs, while centralized stablecoins remain visible. To preserve the ability to convert to fiat, they must maintain an auditable record, which makes them natural points of compliance oversight. Using this visibility, we create an Ethereum dataset of Tether USD (USDT) and USD Coin (USDC) wallet transfers and establish a baseline for behavioral anti-money-laundering (AML) detection. We compare linear models, tree ensembles, deep networks, and graph neural networks. Tree ensembles achieve the best Macro-F1 score, while the graph neural networks lose accuracy as the transaction network fragments. The models separate distinct typologies rather than only flagging suspicion: the fast, dispersed movement of cybercrime wallets is distinguished from the constrained, static footprint of sanctioned or frozen wallets. These results align with the industry shift toward deterministic verification and address the auditability and compliance requirements now forming under regulations such as the EU’s Markets in Crypto-Assets (MiCA) and the U.S. Guiding and Establishing National Innovation for U.S. Stablecoins Act (GENIUS Act), while limiting unjustified asset freezes. A high-precision behavioral classification of suspicious wallets raises the economic cost of financial misconduct and informs compliance practice under emerging stablecoin rules.
Blockchain transaction data exhibit heterogeneous structures, complex interactions, and highly imbalanced distributions, which pose significant challenges for unsupervised anomaly detection. Existing methods often fail to effectively model the intrinsic feature distributions of normal transactions and typically lack interpretability, limiting their reliability and usability in practical blockchain scenarios. To address these issues, this paper proposes an unsupervised anomaly detection framework based on feature distribution learning. The core idea is to explicitly model the distribution of normal transaction behavior in a compact latent space while preserving interpretability. Specifically, a Kolmogorov–Arnold Network (KAN) is employed to learn a two-dimensional latent representation of blockchain transactions, capturing nonlinear relationships between features. During training, the model minimizes the radius of a hypersphere enclosing normal samples, encouraging a compact and structured distribution. During inference, anomalies are identified based on their geometric deviation from the learned distribution, measured by the distance to the latent-space center. This design avoids reliance on reconstruction errors and enables a more direct and stable decision mechanism. Experiments on Ethereum, Blockchain Network Attack Traffic dataset (BNaT) and Real World Dataset of Cryptocurrency Addresses with Transaction Profiles (Real-CATS) demonstrate that the proposed method consistently outperforms state-of-the-art unsupervised baselines across multiple metrics. Furthermore, the symbolic expressions derived from the learned mapping reveal key transaction features that drive anomaly detection decisions, providing clear interpretability. These results highlight the effectiveness, robustness, and practical value of feature distribution learning for blockchain anomaly detection.
With the increase of artificial intelligence (AI) agents being used in the operation of digital systems, they can perform complex tasks, manage resources and interact with distributed environments. However, they require additional support in checking the execution, assigning duties and guaranteeing reliability. Therefore, it is difficult to achieve autonomous decision-making along with stable system operation. Consequently, blockchain is regarded not only as a platform for decentralized applications but also as a dependable base for AI agents. Hence, the present blockchain architectures should not only enhance their efficiency but also ensure traceable state modifications, authentic operations and coordinated communications among various AI-related activities. Therefore, our paper investigates the transaction processing and expanding methods from different perspectives. We classify the previous research into five parts: state control and security measures, improvement of sharding, scalability of consensus and Layer-2 architectures, parallel transaction processing systems and application-oriented trading procedures. For each part, we introduce some typical systems, describe their features in design and evaluate the influences on constructing scalable and trustworthy AI agent systems. Besides, we point out the difficulties in establishing the blockchain framework for AI agents. Finally, this survey presents the existing technologies systematically and highlights their importance.
Secure and scalable electronic medical record (EMR) sharing is essential for cross-institutional collaboration, yet existing blockchain-based approaches can incur high on-chain overhead under bursty, fine-grained, and temporary authorization. We propose Secure and Scalable Tokenized EMR Sharing on a Permissioned Blockchain, referred to as SST-MedChain, a patient-centric framework that (i) enables patient-side non-interactive delegation via an Elliptic Curve Diffie–Hellman (ECDH)-derived verification token protected by a hash commitment, and (ii) reduces on-chain authorization to a near constant-time token lookup and atomic state transition using one-time access tokens. SST-MedChain further supports policy-bounded cascading re-delegation and fast revocation over deployment-bounded delegation chains via a Nested Freezing state machine and a Source Circuit Breaker. Experiments on FISCO BCOS (a permissioned blockchain platform) in a wide area network (WAN) show that, on the evaluated on-chain confirmation path, SST-MedChain improves throughput by 38% and reduces latency by 86% compared with Attribute-Based Access Control (ABAC) at 300 queries per second (QPS), and achieves 16.5% higher throughput than MedShare at 1000 QPS with comparatively stable average confirmation latency.
Autonomous AI agents are increasingly deployed on blockchain platforms, yet the design space that governs their interaction remains poorly understood. This convergence, where autonomous agents operate on and within decentralized systems, is a defining feature of the emerging Web 4.0 paradigm. This paper presents a Systematization of Knowledge organized around a bidirectional trust framework. In the B → A direction, we examine how blockchain provides trust infrastructure for agents, spanning identity and account abstraction, permission and delegation, intent-centric execution, and tokenized agent economies. In the A → B direction, we examine the reverse: how AI agents participate in core blockchain mechanisms including security auditing, consensus, and governance. A Trust Foundation of verifiable computation underpins both directions, with each primitive offering different trade-offs between trust minimality, computational overhead, and deployment readiness. We formalize the interaction as an Agent-Blockchain Interaction Model (ABIM), catalog 70 Ethereum EIPs/ERCs, examine 20 representative industry projects, and review 118 academic papers, applying a five-dimensional framework assessing Verifiability, Minimality of Trust, Expressiveness, Composability, and Maturity. Our analysis uncovers significant gaps: the agent-specific standards ecosystem is overwhelmingly immature, intent architectures lack formal analysis, and while isolated works have begun to explore AI participation in consensus and governance, a unified security framing that treats AI as a first-class actor at the protocol layer remains absent. We propose a three-dimensional taxonomy, identify nine concrete open problems, and highlight the sharpest research opportunities at this intersection.
