Zhi Xue

Parasites in the Toolchain: A Large-Scale Analysis of Attacks on the MCP Ecosystem

Qinsheng Hou, Zihan Zhan, Yanhao Wang, Yu Guo et autres

Large language models(LLMs) are increasingly integrated with external systems through the Model Context Protocol(MCP),which standardizes tool invocation and has rapidly become a backbone for LLM-powered applications. While this paradigm enhances functionality,it also introduces a fundamental security shift:LLMs transition from passive information processors …

cn, hk (code pays fourni par la source)

FreqWF: A Few-shot Website Fingerprinting Attack via Time-Frequency Contrastive Learning

Ziyi Zhou, Weiqi Bai, Xianwen Deng, Yijun Wang et autres

cn (code pays fourni par la source)

Multi-modal Datagram Representation with Spatial-Temporal State Space Models and Inter-flow Contrastive Learning for Encrypted Traffic Classification

Xianwen Deng, Ruijie Zhao, Mingwei Zhan, Shuchen Wu et autres

On the Convergence of Moral Self-Correction in Large Language Models

Guangliang Liu, Bochuan Cao, Zhi Xue, Xitong Zhang et autres

Large Language Models (LLMs) are able to improve their responses when instructed to do so, a capability known as self-correction. When instructions provide only a general and abstract goal without specific details about potential issues in the response, LLMs must rely on …

DISCO: Language-Guided Manipulation With Diffusion Policies and Constrained Inpainting

Hao Ce, Kelvin Lin, Zhi Xue, Siyuan Luo et autres

Diffusion policies have demonstrated strong performance in generative modeling, making them promising for robotic manipulation guided by natural language instructions. However, generalizing language-conditioned diffusion policies to open-vocabulary instructions in everyday scenarios remains challenging due to the scarcity and cost of robot demonstration …

sg (code pays fourni par la source)

Qualitative and quantitative detection of tartrazine in tea powder by mid-infrared spectroscopy and an ensemble of virtual sample generation-based calibration

Hui Chen, Cheng Tan, Qiu Shilin, Chao Tan et autres

cn (code pays fourni par la source)

Detecting Malicious Encrypted Traffic with Multimodal Representations

Xinyu Liu, Ruijie Zhao, Ming Liu, Libo Chen et autres

The rapid advancement of encryption technology enhances network security while enabling hidden attackers to avoid detection. Traditional methods for malicious encrypted traffic detection, which predominantly rely on a single modality such as statistical features or content representations, often fall short of adapting …

cn (code pays fourni par la source)

Countmamba: A Generalized Website Fingerprinting Attack via Coarse-Grained Representation and Fine-Grained Prediction

Xianwen Deng, Yanhao Wang, Mingwei Zhan, Zhi Xue et autres

Tor is the leading low-latency anonymous communication network, widely used to protect users' privacy through mechanisms such as random relay selection. However, despite these defenses, Tor traffic remains susceptible to website finger-printing (WF) attacks, where attackers analyze side-channel information (e.g., packet size, …

cn, bd (code pays fourni par la source)

Dr. Docker: A Large-Scale Security Measurement of Docker Image Ecosystem

Hequan Shi, Lingyun Ying, Libo Chen, Haixin Duan et autres

Docker has transformed modern software development, enabling the widespread reuse of containerized applications. Currently, Docker images are primarily distributed through centralized registries, among which Docker Hub is the largest, allowing developers to share and reuse images easily. The threats within these images …

cn (code pays fourni par la source)

A combined feature selection approach for malicious email detection based on a comprehensive email dataset

Han Zhang, Ming Liu, Libo Chen, Songyang Wu et autres

Abstract In recent years, new malicious email attacks have emerged. We summarize two major challenges in the current field of malicious email detection using machine learning algorithms. (1) Current works on malicious email detection use different datasets and lack a unified and …

cn (code pays fourni par la source)

Lightweight intrusion detection methods based on artificial intelligence for IoT networks

Guan Gui, Zhi Xue, Ruijie Zhao, Xianwen Deng et autres

cn (code pays fourni par la source)

Characterization of the Freshness of Pork by Near-Infrared Spectroscopy (NIRS) and Ensemble Learning

Cheng Tan, Hui Chen, Miao Zeng, Zhi Xue

Pork is a perishable food and often needs to be stored in the refrigerator to maintain its quality as much as possible. Traditional methods for discriminating fresh and refrigerated pork are subjective, time-consuming, or destructive. The feasibility of using near-infrared (NIR) spectroscopy …

cn (code pays fourni par la source)