Institution profile

Jinan University

Academic institutionasia · cn
Official website
Research library460linked papers
Opportunities0open roles
Selected work

Representative Papers

CheatAgent: Attacking LLM-Empowered Recommender Systems via LLM Agent

Aug 24, 2024Knowledge Discovery and Data Mining

This work investigates security vulnerabilities in LLM-augmented recommender systems (RecSys) under black-box settings—a previously unexplored threat scenario. Method: We propose the first adversarial attack framework leveraging an LLM-based agent, which identifies high-impact text insertion positions via position-aware mechanisms, generates semantically preserved and minimally perturbed adversarial texts, and iteratively refines prompts using black-box query feedback. Crucially, the LLM itself serves as the attack agent, enabling efficient, stealthy, and cross-model transferable attacks. Contribution/Results: Extensive experiments on three real-world datasets demonstrate that our framework significantly outperforms conventional reinforcement learning–based attacks: it achieves higher attack success rates, requires fewer API queries, and induces smaller textual perturbations. These results empirically expose previously underappreciated, substantive security and privacy risks inherent in LLM-RecSys architectures.

14 citations1 influentialRead paper

Optimizing System Latency for Blockchain-Encrypted Edge Computing in Internet of Vehicles

Jun 17, 2025Computers, Materials & Continua

To address the dual challenges of adversarial external attacks and high latency induced by blockchain integration in Internet of Vehicles (IoV) edge task offloading, this paper proposes a secure, low-latency edge computing framework incorporating the Raft consensus mechanism. We pioneer the integration of a lightweight Raft protocol into the IoV edge architecture to establish a tamper-resistant and verifiable task offloading security mechanism. An end-to-end latency analytical model is developed to characterize the coupled delays arising from communication, computation, and consensus. Subsequently, a convex-optimization-based joint resource-consensus scheduling algorithm is designed to achieve Pareto-optimal trade-offs between security and latency. Simulation results demonstrate that, compared with baseline schemes, the proposed framework reduces average system latency by 32.7%, decreases latency standard deviation by 41.5%, and achieves a data extraction rate of 99.2%, thereby satisfying IoV requirements for millisecond-level responsiveness and high reliability.

1 citationsRead paper

Forecasting realized volatility in the stock market: a path-dependent perspective

Mar 02, 2025

To address insufficient predictive accuracy for stock market realized volatility, this paper proposes the HAR-PD model family, which integrates path-dependence characteristics into the Heterogeneous Autoregressive (HAR) framework—marking the first incorporation of path-dependent volatility decomposition into HAR modeling. The core innovation is the HAR-REQ model, which dynamically identifies trend and reversal patterns in price paths using empirically determined quantile thresholds, thereby explicitly capturing volatility’s long- and short-term memory effects and asymmetric responses. Empirical analysis on high-frequency data from the Shanghai and Shenzhen stock markets demonstrates that HAR-PD models significantly outperform the benchmark HAR model, reducing average MAE by 12.6% and RMSE by 11.3%. Robustness is confirmed through rolling-window estimation, subsample analysis, and alternative volatility measures. This work introduces a novel path-dependent perspective to volatility modeling and provides an interpretable, statistically grounded toolkit for practitioners and researchers.

1 citationsRead paper

DGFM: Full Body Dance Generation Driven by Music Foundation Models

Feb 27, 2025

To address the limited representational capacity of hand-crafted features and the underutilization of music foundation models in music-driven dance generation, this paper proposes a multi-granularity music feature fusion framework. We are the first to incorporate music foundation models—such as MusicLM—into dance generation, jointly leveraging their high-level semantic representations with low-level temporal features (e.g., MFCCs, chroma, tempo) to condition a cross-modal diffusion model. Our method employs hierarchical feature alignment and a gated fusion mechanism to jointly model musical semantics and rhythmic structure, enabling high-fidelity, temporally synchronized 3D full-body dance sequence generation. Extensive evaluations demonstrate significant improvements over four variants of music foundation models and two categories of hand-crafted feature baselines across multiple standard metrics. The generated motions achieve state-of-the-art realism and music-motion temporal alignment accuracy.

1 citationsRead paper
Recent publications

Latest Papers