arXiv subjects

Yinfeng Cao

Publications and source records attributed to Yinfeng Cao.

8 recordsLinked to original sources

arXiv2026

When Ad Networks Misbehave: Understanding Risks of Semi-Drive-By Splash Ads

We investigate the mobile splash ads ecosystem, i.e., full-screen advertisements shown at app launch, where monetization relies on interaction signals that are difficult to verify end-to-end. This setting is especially sensitive because incidental touches and sensor-driven callbacks are common yet easy to misattribute as engagement. Prior work has largely framed mobile ad fraud as a publisher-side problem, while some studies attribute fraudulent operations to embedded ad libraries. Yet an important risk remains underexplored: ad SDKs control how interaction signals are interpreted, measured, and reported, creating an opportunity to reinterpret ambiguous user or device signals as valid advertising interactions. We uncover a previously less-known form of fraud at the ad-network layer in which splash ads are triggered not by intentional user actions but by incidental or indirect interactions, which we term semi-drive-by splash ads. By translating non-ad interactions into billable engagement events, ad networks can inflate performance metrics, overcharge advertisers, and erode user trust. To expose this behavior in the wild, we design AdHive, an automated honeypot-like analysis framework that induces evasive splash-ad delivery and landing behaviors under realistic device conditions. AdHive reproduces human-like activity through LLM-generated usage traces and sensor dynamics, enabling execution paths that remain hidden in conventional analysis environments. Our large-scale measurement across thousands of popular Android applications shows that semi-drive-by splash ads are widespread and are often triggered by subtle signals such as minor sensor variations. We further confirm real-world impact by working with one of China's largest advertisers, identifying multiple ad networks engaging in this fraud and leading to enforced repayments of about 4 million Yuan (approximately US$600,000).

cs.CR↗

arXiv2026

S$^2$GS: Structured Sparse Gaussian Streaming for Efficient Free-Viewpoint Video Reconstruction on Edge-IoT Devices

Streaming reconstruction of Free-Viewpoint Videos (FVVs) supports immersive Internet of Things (IoT) services, such as telepresence and digital twin visualization. Existing methods suffer from high per-frame optimization time and large storage footprints, limiting deployment on resource-constrained Edge-IoT devices. To address these challenges, we propose Structured Sparse Gaussian Streaming (S$^2$GS), an FVV reconstruction framework that exploits structure-aware temporal sparsity to selectively update Gaussian residuals, enabling efficient streaming without compromising visual fidelity. In the spatial domain, a streaming octree hierarchically organizes Gaussian residuals, capturing spatial correlations that guide residual updates. In the temporal domain, a structured gating mechanism, comprising hierarchical feature propagation (HFP) and Gumbel-Sigmoid sampling, converts hierarchical dynamic cues into sparse residual update decisions under differentiable optimization. A multi-level discrete scheme is further adopted to provide fine-grained control over residual updates while preserving intricate dynamic details. Extensive experiments across consumer GPUs, industrial edge IoT devices, and a physical telepresence testbed demonstrate that S$^2$GS consistently reduces per-frame optimization time and storage footprint while maintaining competitive visual quality. Compared with QUEEN, S$^2$GS reduces per-frame optimization time by 59% and storage costs by 85% on an RTX 4090 GPU. On the Jetson AGX Orin, S$^2$GS delivers the highest rendering throughput (60+ FPS) and the lowest energy consumption among the evaluated methods, demonstrating its potential for deployment in resource-constrained systems.

cs.CV↗

arXiv2026

FedCCA: Client-Centric Adaptation against Data Heterogeneity in Federated Learning on IoT Devices

With the rapid development of the Internet of Things (IoT), AI model training on private data such as human sensing data is highly desired. Federated learning (FL) has emerged as a privacy-preserving distributed training framework for this purpuse. However, the data heterogeneity issue among IoT devices can significantly degrade the model performance and convergence speed in FL. Existing approaches limit in fixed client selection and aggregation on cloud server, making the privacy-preserving extraction of client-specific information during local training challenging. To this end, we propose Client-Centric Adaptation federated learning (FedCCA), an algorithm that optimally utilizes client-specific knowledge to learn a unique model for each client through selective adaptation, aiming to alleviate the influence of data heterogeneity. Specifically, FedCCA employs dynamic client selection and adaptive aggregation based on the additional client-specific encoder. To enhance multi-source knowledge transfer, we adopt an attention-based global aggregation strategy. We conducted extensive experiments on diverse datasets to assess the efficacy of FedCCA. The experimental results demonstrate that our approach exhibits a substantial performance advantage over competing baselines in addressing this specific problem.

cs.LG↗

arXiv2025

Geometry-Consistent 4D Gaussian Splatting for Sparse-Input Dynamic View Synthesis

Gaussian Splatting has been considered as a novel way for view synthesis of dynamic scenes, which shows great potential in AIoT applications such as digital twins. However, recent dynamic Gaussian Splatting methods significantly degrade when only sparse input views are available, limiting their applicability in practice. The issue arises from the incoherent learning of 4D geometry as input views decrease. This paper presents GC-4DGS, a novel framework that infuses geometric consistency into 4D Gaussian Splatting (4DGS), offering real-time and high-quality dynamic scene rendering from sparse input views. While learning-based Multi-View Stereo (MVS) and monocular depth estimators (MDEs) provide geometry priors, directly integrating these with 4DGS yields suboptimal results due to the ill-posed nature of sparse-input 4D geometric optimization. To address these problems, we introduce a dynamic consistency checking strategy to reduce estimation uncertainties of MVS across spacetime. Furthermore, we propose a global-local depth regularization approach to distill spatiotemporal-consistent geometric information from monocular depths, thereby enhancing the coherent geometry and appearance learning within the 4D volume. Extensive experiments on the popular N3DV and Technicolor datasets validate the effectiveness of GC-4DGS in rendering quality without sacrificing efficiency. Notably, our method outperforms RF-DeRF, the latest dynamic radiance field tailored for sparse-input dynamic view synthesis, and the original 4DGS by 2.62dB and 1.58dB in PSNR, respectively, with seamless deployability on resource-constrained IoT edge devices.

cs.CV↗

arXiv2025

PolyLink: A Blockchain Based Decentralized Edge AI Platform for LLM Inference

The rapid advancement of large language models (LLMs) in recent years has revolutionized the AI landscape. However, the deployment model and usage of LLM services remain highly centralized, creating significant trust issues and costs for end users and developers. To address these issues, we propose PolyLink, a blockchain-based decentralized AI platform that decentralizes LLM development and inference. Specifically, PolyLink introduces a decentralized crowdsourcing architecture that supports single-device and cross-device model deployment and inference across heterogeneous devices at the edge. Moreover, to ensure the inference integrity, we design the TIQE protocol, which combines a lightweight cross-encoder model and an LLM-as-a-Judge for a high-accuracy inference evaluation. Lastly, we integrate a comprehensive token-based incentive model with dynamic pricing and reward mechanisms for all participants. We have deployed PolyLink and conducted an extensive real-world evaluation through geo-distributed deployment across heterogeneous devices. Results indicate that the inference and verification latency is practical. Our security analysis demonstrates that the system is resistant to model degradation attacks and validator corruptions. PolyLink is now available at https://github.com/IMCL-PolyLink/PolyLink.

cs.CR↗

arXiv2024

MAP the Blockchain World: A Trustless and Scalable Blockchain Interoperability Protocol for Cross-chain Applications

Blockchain interoperability protocols enable cross-chain asset transfers or data retrievals between isolated chains, which are considered as the core infrastructure for Web 3.0 applications such as decentralized finance protocols. However, existing protocols either face severe scalability issues due to high on-chain and off-chain costs, or suffer from trust concerns because of centralized designs. In this paper, we propose \texttt{MAP}, a trustless blockchain interoperability protocol that relays cross-chain transactions across heterogeneous chains with high scalability. First, within \texttt{MAP}, we develop a novel \textit{cross-chain relay} technique, which integrates a unified relay chain architecture and on-chain light clients of different source chains, allowing the retrieval and verification of diverse cross-chain transactions. Furthermore, we reduce cross-chain verification costs by incorporating an optimized zk-based light client scheme that adaptively decouples signature verification overheads from inefficient smart contract execution and offloads them to off-chain provers. For experiments, we conducted the first large-scale evaluation on existing interoperability protocols. With \texttt{MAP}, the required number of on-chain light clients is reduced from $O(N^2)$ to $O(N)$, with around 35\% reduction in on-chain costs and 25\% reduction for off-chain costs when verifying cross-chain transactions. To demonstrate the effectiveness, we deployed \texttt{MAP} in the real world. By 2024, we have supported over six popular public chains, 50 cross-chain applications and relayed over 200K cross-chain transactions worth over 640 million USD. Based on rich practical experiences, we constructed the first real-world cross-chain dataset to further advance blockchain interoperability research.

cs.CR↗

arXiv2024

Ormer: A Manipulation-resistant and Gas-efficient Blockchain Pricing Oracle for DeFi

Price feeds of cryptocurrencies are essential for Decentralized Finance (DeFi) applications to realize fundamental trading and exchanging functionalities, which are retrieved from external price data sources such as exchanges and input to on-chain smart contracts in real-time. Currently, arithmetic mean based time-weighted average price (TWAP) oracles are widely used to process price feeds by averaging asset price with short time frame to achieve reliable and gas-efficient pricing. However, recent research indicates that TWAP is vulnerable to price manipulation attacks, resulting in abnormal price fluctuations and severe financial loss. Even worse, TWAP oracles usually set a relatively long time frame setting to prevent such attack. However, it would further introduce long delays and high price deviation errors from the market asset price. To address this issue, we propose a novel on-chain gas-efficient pricing algorithm (Ormer) that heuristically estimates the median of asset price within an observation window based on a piecewise-parabolic formula, while the time delay is suppressed by fusing estimations with different window sizes. Our evaluation based on multiple pairs of token swapping price feed across different chains show that Ormer reduces the mean absolute price error by 15.3% and the time delay by 49.3% compared to TWAP. For gas efficiency, regardless of the number of price observations, an encoding mechanism with constant storage requirement is employed without saving all the historical data for median estimation. Surprisingly, the lowest gas consumption of Ormer is even 15.2% less than TWAP, and the oracle querying fee would be saved up to ~20K USD per day for DeFi participants.

cs.CR↗

arXiv2022

Security and Privacy in Big Data Sharing: State-of-the-Art and Research Directions

Big Data Sharing (BDS) refers to the act of the data owners to share data so that users can find, access and use data according to the agreement. In recent years, BDS has been an emerging topic due to its wide applications, such as big data trading and cross-domain data analytics. However, as the multiple parties are involved in a BDS platform, the issue of security and privacy violation arises. There have been a number of solutions for enhancing security and preserving privacy at different big data operations (e.g., data operation, data searching, data sharing and data outsourcing). To the best of our knowledge, there is no existing survey that has particularly focused on the broad and systematic developments of these security and privacy solutions. In this study, we conduct a comprehensive survey of the state-of-the-art solutions introduced to tackle security and privacy issues in BDS. For a better understanding, we first introduce a general model for BDS and identify the security and privacy requirements. We discuss and classify the state-of-the-art security and privacy solutions for BDS according to the identified requirements. Finally, based on the insights gained, we present and discuss new promising research directions.

cs.CR↗