Cross-chain technology, as a key driver for enhancing interoperability of blockchains, enables asset transfer and exchange between different blockchains. At present, cross-chain models based on light clients are widely adopted due to their fully decentralized nature and applicability to diverse scenarios. However, the rapid advancement of on-chain analysis techniques, such as address linkage and fund flow tracking, has significantly increased risks of de-anonymization in cross-chain transactions, posing serious privacy challenges. In this paper, we propose SharedRXC, a privacy-preserving asset cross-chain scheme for the light-client cross-chain model, which guarantees address unlinkability without extra privacy trust assumptions. First, to hide cross-chain addresses during interchain transmission, we propose the Ring Account (RA) to replace a single address for sending or receiving funds. In addition, we propose a zero-knowledge proof-based method to verify virtual identity ownership, allowing the virtual identity to track fund balances without exposing the addresses. Second, to prevent the exposure of the link between an address and its virtual identity caused by fund amount differences during deposits or withdrawals, which would compromise address unlinkability, we propose the Shared Burn/Mint method to obscure on chain fund change differences. Based on the liability equalization mechanism, we design two privacy-preserving cross-chain protocols: the cross-chain asset transfer (SharedRXC.T) and exchange (SharedRXC.E) protocols. Finally, we evaluateSharedRXC.TandSharedRXC.E, which reduce gas costs by 30% to 40% compared to zkCross and achieve execution times in the millisecond range. Therefore, SharedRXC provides a practical privacy-preserving solution for cross-chain financial applications in the multi-chain ecosystem.

Recently, there is a surge in ransomware activities that encrypt users’ sensitive data and demand bitcoins for ransom payments to conceal the criminal’s identity. It is crucial for regulatory agencies to identify as many ransomware addresses as possible to accurately estimate the impact of these ransomware activities. However, existing methods for detecting ransomware addresses rely primarily on time-consuming data collection and clustering heuristics, and they face two major issues: (1) The features of an address itself are insufficient to accurately represent its activity characteristics, and (2) the number of disclosed ransomware addresses is extremely less than the number of unlabeled addresses. These issues lead to a significant number of ransomware addresses being undetected, resulting in a substantial underestimation of the impact of ransomware activities. To solve the above two issues, we propose an optimized ransomware address detection method based on Bitcoin transaction relationships, named XRAD , to detect more ransomware addresses with high performance. To address the first one, we present a cascade feature extraction method for Bitcoin transactions to aggregate features of related addresses after exploring transaction relationships. To address the second one, we build a classification model based on Positive-unlabeled learning to detect ransomware addresses with high performance. Extensive experiments demonstrate that XRAD significantly improves average accuracy, recall, and F1 score by 15.07%, 19.71%, and 34.83%, respectively, compared to state-of-the-art methods. In total, XRAD detects 120,335 ransomware activities from 2009 to 2023, revealing a development trend and average ransom payment per year that aligns with three reports by FinCEN, Chainalysis, and Coveware.

Mediation analysis learns the causal effect transmitted via mediator variables between treatments and outcomes, and receives increasing attention in various scientific domains to elucidate causal relations. Most existing works focus on point-exposure studies where each subject only receives one treatment at a single time point. However, there are a number of applications (e.g., mobile health) where the treatments are sequentially assigned over time and the dynamic mediation effects are of primary interest. Proposing a reinforcement learning (RL) framework, we are the first to evaluate dynamic mediation effects in settings with infinite horizons. We decompose the average treatment effect into an immediate direct effect, an immediate mediation effect, a delayed direct effect, and a delayed mediation effect. Upon the identification of each effect component, we further develop robust and semi-parametrically efficient estimators under the RL framework to infer these causal effects. The superior performance of the proposed method is demonstrated through extensive numerical studies, theoretical results, and an analysis of a mobile health dataset. A Python implementation of the proposed procedure is available at https://github.com/linlinlin97/MediationRL.

Reinforcement learning (RL) is a powerful technique that allows an autonomous agent to learn an optimal policy to maximize the expected return. The optimality of various RL algorithms relies on the stationarity assumption, which requires time-invariant state transition and reward functions. However, deviations from stationarity over extended periods often occur in real-world applications like robotics control, health care and digital marketing, resulting in suboptimal policies learned under stationary assumptions. In this paper, we propose a model-based doubly robust procedure for testing the stationarity assumption and detecting change points in offline RL settings with certain degree of homogeneity. Our proposed testing procedure is robust to model misspecifications and can effectively control type-I error while achieving high statistical power, especially in high-dimensional settings. Extensive comparative simulations and a real-world interventional mobile health example illustrate the advantages of our method in detecting change points and optimizing long-term rewards in high-dimensional, non-stationary environments.

As a popular game around the world, Snakes has multiple modes with different settings. In this work, we are dedicated to the 3v3 Snakes, which is characterized by a complex mixture of competition and cooperation. To address this mode of Snakes, most existing AI agents adopt rule based methods, which achieve limited performance due to human’s oversight of some special circumstances. Inspired by the superiority of multi-agent reinforcement learning (MARL), we propose a rule-enhanced multi-agent reinforcement learning algorithm and build a 3v3 Snakes AI. Specifically, we introduce the territory matrix which is commonly utilized in rule based methods to the state features and mask the illegal actions through designed rules. The relationships of individual-team and friends-foes are also merged into reward design. Trained with Distributed PPO and self-play on a single GeForce RTX 2080 GPU for twenty-four hours, our AI achieves state-of-the-art performance and beats human players. On JIDI platform, our agent outperforms the other 132 participating agents and ranks the first for more than 20 consecutive days.