Institution profile

Huazhong University of Science and Technology

Academic institutionasia · cn
Official website
Research library1,607linked papers
Opportunities0open roles
Selected work

Representative Papers

Prompt Injection attack against LLM-integrated Applications

Jun 08, 2023arXiv.org

Prompt injection attacks pose an increasingly severe security threat to large language model (LLM) integrated applications, yet existing black-box attack methods suffer from limited practical efficacy. Method: This paper proposes HouYi—the first real-world-oriented, three-stage black-box prompt injection framework comprising pre-prompt injection, context-aware segmentation, and malicious payload delivery. HouYi uniquely enables automated triggering of high-impact consequences—including arbitrary LLM misuse and application-level prompt stealing—via black-box fuzzing, context-aware prompt engineering, and web-injection-inspired modeling. Contribution/Results: Evaluated through real-world penetration testing across 36 mainstream LLM applications, HouYi uncovered 31 critical vulnerabilities, independently confirmed by ten vendors—including Notion—with impact on millions of users. The work significantly advances LLM security practice by bridging the gap between theoretical attack models and deployable, scalable exploitation techniques.

536 citations38 influentialRead paper

TrimCaching: Parameter-sharing Edge Caching for AI Model Downloading

Apr 22, 2024arXiv.org

Existing edge caching mechanisms for AI model delivery in 5G/6G networks overlook parameter-block reuse—e.g., shared knowledge units across CNNs or LLMs—leading to low storage efficiency and limited cache hit rates under stringent latency constraints. Method: We propose a parameter-sharing-aware edge model caching framework that, for the first time, formulates parameter-block reuse as a submodular optimization problem. We design a polynomial-time algorithm with theoretical approximation guarantees and provide a general greedy solution. The framework jointly optimizes storage efficiency and service latency in multi-edge wireless networks. Results: Simulation results demonstrate that our approach significantly improves cache hit rates over conventional content-based caching, validating the effectiveness and practicality of parameter-level sharing for edge AI deployment.

12 citationsRead paper

LightningRL: Breaking the Accuracy-Parallelism Trade-off of Block-wise dLLMs via Reinforcement Learning

Mar 04, 2026arXiv.org

This work addresses the challenge of balancing generation quality and parallelism in block-wise speculative decoding for large language models (dLLMs), where increased parallel generation often leads to degraded accuracy and instability. To overcome this trade-off, the authors propose LightningRL, a novel framework that leverages reinforcement learning to optimize the speed–quality Pareto frontier of dLLMs for the first time. Built upon Group Relative Policy Optimization (GRPO), LightningRL introduces throughput-per-fidelity (TPF)-aware sampling, decoupled reward normalization, and token-level negative log-likelihood regularization to dynamically reinforce accurate generation trajectories under high parallelism. Experiments demonstrate that LightningRL significantly advances the Pareto frontier on mathematical and code generation tasks, achieving an average of 7.32 tokens per forward pass (peaking at 11.10 on MBPP) while maintaining competitive accuracy.

5 citationsRead paper

Pedestrian Trajectory Prediction Based on Social Interactions Learning With Random Weights

Jan 13, 2025IEEE transactions on multimedia

To address the limitations of rule-based pedestrian trajectory prediction in autonomous driving—particularly the difficulty in modeling implicit social interactions—this paper proposes DTGAN, the first generative adversarial framework specifically designed for graph-structured sequential data. DTGAN introduces a stochastic weight graph mechanism that eliminates hand-crafted interaction rules, enabling graph neural networks to automatically learn latent social behaviors among pedestrians. Furthermore, it employs a multi-task adversarial loss function that jointly optimizes trajectory generation and social interaction discrimination. Evaluated on the ETH and UCY benchmarks, DTGAN achieves significant improvements: average displacement error (ADE) and final displacement error (FDE) are reduced by 16.7% and 39.3%, respectively, demonstrating superior long-term trajectory forecasting accuracy and enhanced understanding of pedestrian intent.

5 citationsRead paper

Stable-DiffCoder: Pushing the Frontier of Code Diffusion Large Language Model

Jan 22, 2026

This work addresses the longstanding performance gap between diffusion-based and autoregressive large language models for code, where diffusion models typically underperform under comparable resource constraints. Building upon the Seed-Coder architecture and dataset, the authors introduce block-wise diffusion with continuous pretraining, enhanced by a tailored warm-up strategy and a block-level truncated noise schedule to enable efficient and stable training. Under identical architectural and data conditions, this approach enables diffusion models to consistently surpass autoregressive baselines, achieving substantial improvements in structured code editing, reasoning, and low-resource language modeling. Notably, using only pretraining and supervised fine-tuning, the proposed method outperforms a range of 8B-scale autoregressive and diffusion models across multiple code benchmarks.

4 citations1 influentialRead paper
Recent publications

Latest Papers