In recent years, blockchain technology has developed rapidly and received widespread attention. However, its pseudonymous and decentralized nature has also attracted many criminal activities. Ponzi schemes, a kind of classic financial scam, also hide their true face in smart contracts, causing massive financial losses to blockchain users. Although several methods have been proposed to detect Ponzi contracts, there are still limitations in broad applicability, semantics understanding, and adversarial robustness. In this article, we propose PonziHunter, an intelligent framework for hunting Ponzi contracts on Ethereum. To tackle the problem of broad applicability, we train a detection model that does not require expert experience based on publicly available on-chain bytecode and off-chain contract labels. To tackle the problem of semantics understanding, we employ cross-function control flows and state variable dependencies to understand the logic of Ponzi contracts. Specifically, we decompile bytecodes into higher-order representations to analyze control flows and state variable dependencies and model the information as graph data. By combining the idea of code slicing, we identify the basic blocks related to Ponzi contract recognition. To tackle the problem of adversarial robustness, we model Ponzi contract recognition as a graph classification problem based on contrastive pre-training. We propose a data augmentation method for control flow graphs (CFGs), which preserves the basic blocks related to Ponzi contract recognition as much as possible during data perturbation. Experimental results show that PonziHunter outperforms state-of-the-art tools with average improvements of at least 4.77% on real-world ground-truth data and can newly discover 85 Ponzi contracts in the wild. More importantly, PonziHunter is robust against adversarial examples and can locate the critical basic blocks for smart Ponzi detection.

In recent years, phishing scams have caused huge economic losses in Ethereum, the largest blockchain platform enabling smart contracts. Many new sorts of phishing attacks based on smart contracts, specifically targeting Ethereum assets such as Ether and tokens, are emerging. Existing Ethereum phishing detection methods usually mine the transaction relationships among accounts from block data, while neglecting to mine the temporal transaction patterns inherent in the accounts themselves in different transaction types introduced by smart contracts. Such information provides a new perspective for analyzing account transaction preferences. However, since this information is hidden in heterogeneous data such as trace data and event logs, it is difficult to analyze and mine the information. In this paper, we contribute Trans2Graph, a novel graph-based framework for Ethereum data modeling and phishing detection, to fully exploit the massively heterogeneous temporal transaction data. We propose a new paradigm for the fusion of heterogeneous Ethereum data and model the implicit transition relationships among multiple heterogeneous transactions of each Ethereum account into a heterogeneous, temporal, directed multigraph called transaction state transition graph. Empirical analysis shows that phishing accounts have unique patterns in both the heterogeneity and time dynamics of transaction state transition graphs. Based on the analysis, we develop a novel attention-based graph neural network for the learning of heterogeneous temporal state transition graphs and phishing detection. Experiments on a large-scale real-world dataset demonstrate that Trans2Graph achieves a minimum 52.57% improvement in the average precision metric on state-of-the-art account interaction graph-based methods and a minimum 11.52% improvement in average precision on transaction sequence-based methods.

As one of the most typical cybercrime types, phishing scams have extended the devil’s hand to the emerging blockchain ecosystem in recent years. Especially, huge economic losses have been caused by phishing scams in Ethereum, the second-largest blockchain system. Existing approaches for Ethereum phishing detection, however, typically use machine learning or transaction graph embedding methods to identify phishers in isolation and do not effectively uncover the group of transaction accounts linked to scams (which we term a “gang”). Since accounts are pseudonymous in Ethereum, these undisclosed conspirator accounts have potential risks to the system. In this paper, we conduct the first study that characterizes and detects Ethereum phishing gangs. We first investigate the transaction behaviors in phishing gangs from the perspectives of individuals, pairs, and higher-order patterns. Our analysis reveals that although the Ethereum transaction graph is sparse with a highly skewed degree distribution, phishing accounts in the same gang have closer relationships and share specific transaction patterns. Based on our findings, we formalize the phishing gang detection problem and introduce a novel detection model named PGDetector. Given a risky phishing account as a seed, PGDetector can find out the potential risky accounts sharing close relationships within the seed’s community based on genetic algorithm optimization. Experimental results on large-scale Ethereum transaction data demonstrate the effectiveness of PGDetector.

Event cameras, such as dynamic vision sensors (DVS), are biologically inspired vision sensors that have advanced over conventional cameras in high dynamic range, low latency and low power consumption, showing great application potential in many fields. Event cameras are more sensitive to junction leakage current and photocurrent as they output differential signals, losing the smoothing function of the integral imaging process in the RGB camera. The logarithmic conversion further amplifies noise, especially in low-contrast conditions. Recently, researchers proposed a series of datasets and evaluation metrics but limitations remain: 1) the existing datasets are small in scale and insufficient in noise diversity, which cannot reflect the authentic working environments of event cameras; and 2) the existing denoising evaluation metrics are mostly referenced evaluation metrics, relying on APS information or manual annotation. To address the above issues, we construct a large-scale event denoising dataset (multilevel benchmark for event denoising, E-MLB) for the first time, which consists of 100 scenes, each with four noise levels, that is 12 times larger than the largest existing denoising dataset. We also propose the first nonreference event denoising metric, the event structural ratio (ESR), which measures the structural intensity of given events. ESR is inspired by the contrast metric, but is independent of the number of events and projection direction. Based on the proposed benchmark and ESR, we evaluate the most representative denoising algorithms, including classic and SOTA, and provide denoising baselines under various scenes and noise levels. The corresponding results and codes are available athttps://github.com/KugaMaxx/cuke-emlb.

Overdue risk detection of consumer loans is a critical issue faced by consumer finance companies. Unlike other types of loans, such as mortgage loans and guaranteed loans, consumer loans only regard personal credit as collateral. As a high overdue rate will result in economic losses to financial companies, it is of great significance for lenders to accurately detect risky customers. However, the large volume of credit data and the variety of customer characteristics make the risk detection via manual expert analysis rather challenging. Additionally, previous loan risk detection approaches based on machine learning classification neglect the relations between different customers, and traditional graph neural networks lack the exploration of loan overdue patterns. In this paper, we construct a heterogeneous graph based on real credit data from a consumer finance company. We analyze the distribution of meta-paths and propose a meta-path-based graph neural network that combines both lower-order and higher-order features. Experimental results show that our model is able to detect more risky customers by exploring overdue patterns and can achieve the best effect in the loan overdue detection task.

Dynamic Vision Sensor (DVS) can asynchronously output the events reflecting apparent motion of objects with microsecond resolution, and shows great application potential in monitoring and other fields. However, the output event stream of existing DVS inevitably contains background activity noise (BA noise) due to dark current and junction leakage current, which will affect the temporal correlation of objects, resulting in deteriorated motion estimation performance. Particularly, the existing filter-based denoising methods cannot be directly applied to suppress the noise in event stream, since there is no spatial correlation. To address this issue, this paper presents a novel progressive framework, in which a Motion Estimation (ME) module and an Event Denoising (ED) module are jointly optimized in a mutually reinforced manner. Specifically, based on the maximum sharpness criterion, ME module divides the input event into several segments by adaptive clustering in a motion compensating warp field, and captures the temporal correlation of event stream according to the clustered motion parameters. Taking temporal correlation as guidance, ED module calculates the confidence that each event belongs to real activity events, and transmits it to ME module to update energy function of motion segmentation for noise suppression. The two steps are iteratively updated until stable motion segmentation results are obtained. Extensive experimental results on both synthetic and real datasets demonstrate the superiority of our proposed approaches against the State-Of-The-Art (SOTA) methods.