arXiv subjects

Biwei Yan

Publications and source records attributed to Biwei Yan.

8 recordsLinked to original sources

arXiv2026

"What Happens Locally, Leaks Globally": Detecting Privacy Leakage Risks in MCP Servers

The Model Context Protocol (MCP) has rapidly become the de facto standard for connecting large language models (LLMs) to external resources, but it also introduces a class of privacy risks that existing tools are ill-equipped to detect. Unlike conventional exfiltration bugs, leakage in MCP servers is largely protocol-induced: credentials, API keys, and Personally Identifiable Information (PII) cross the local/LLM boundary simply by being returned, logged, or raised inside a tool handler, with no explicit outbound request in the source code. We present MCPPrivacyDetector, a context-aware cross-language static analysis framework that detects such leakage in multilingual MCP servers. MCPPrivacyDetector lifts heterogeneous code implemented across different programming language (e.g., Python) into a unified program representation, applies context-aware semantic filtering to isolate genuinely sensitive values and protocol-specific implicit sinks (e.g., @mcp.tool handlers), and performs taint analysis to enumerate feasible flows. Applied to 10,655 real-world MCP servers, MCPPrivacyDetector finds leakage rates above 10%. Case studies confirm concrete exposures including leaked Bearer tokens, propagated API keys, and plaintext authentication credentials, arguing for systematic, protocol-aware safeguards in the emerging LLM agent toolchain.

cs.CR↗

arXiv2026

MIRAGE: Stealthy Visual Prompt Injection for Vulnerability Detection in Web Agents

Multimodal Large Language Model (MLLM)-based web agents provide practical, high-precision solutions for visual browser automation; however, they inherently expand the attack surface, introducing novel vision-based vulnerabilities. Existing adversarial evaluations targeting these agents frequently rely on permissive threat models and visually conspicuous artifacts. In this paper, we investigate a constrained vulnerability detection setting: a trusted web platform where the evaluator acts solely as an unprivileged third party, such as a merchant or advertiser, controlling only a semantically legitimate, spatially constrained region, such as an ad slot, a sponsored card, or a localized widget. Operating under these realistic constraints, we propose MIRAGE, a novel visual indirect prompt injection framework for targeted next-action hijacking. Our approach leverages diffusion models to generate perceptually benign adversarial images strictly confined to the attacker-controlled boundaries permitted by the trusted service provider. To maximize attack efficacy within such a restrictive setting, we introduce a robust optimization technique combining curvature-aware adversarial diffusion guidance with sparse, dark-pixel residual perturbations. Comprehensive evaluations against prominent MLLM web agent frameworks, specifically SeeAct and OpenClaw, empirically demonstrate the potency, realism, and stealth of our proposed MIRAGE.

cs.CV↗

arXiv2026

Give Them an Inch and They Will Take a Mile:Understanding and Measuring Caller Identity Confusion in MCP-Based AI Systems

The Model Context Protocol (MCP) is an open and standardized interface that enables large language models (LLMs) to interact with external tools and services, and is increasingly adopted by AI agents. However, the security of MCP-based systems remains largely unexplored.In this work, we conduct a large-scale security analysis of MCP servers integrated within MCP clients. We show that treating MCP servers as trusted entities without authenticating the caller identity is fundamentally insecure. Since MCP servers often cannot distinguish who is invoking a request, a single authorization decision may implicitly grant access to multiple, potentially untrusted callers.Our empirical study reveals that most MCP servers rely on persistent authorization states, allowing tool invocations after an initial authorization without re-authentication, regardless of the caller. In addition, many MCP servers fail to enforce authentication at the per-tool level, enabling unauthorized access to sensitive operations.These findings demonstrate that one-time authorization and server-level trust significantly expand the attack surface of MCP-based systems, highlighting the need for explicit caller authentication and fine-grained authorization mechanisms.

cs.CR↗

arXiv2026

Don't believe everything you read: Understanding and Measuring MCP Behavior under Misleading Tool Descriptions

The Model Context Protocol (MCP) enables large language models to invoke external tools through natural-language descriptions, forming the foundation of many AI agent applications. However, MCP does not enforce consistency between documented tool behavior and actual code execution, even though MCP Servers often run with broad system privileges. This gap introduces a largely unexplored security risk. We study how mismatches between externally presented tool descriptions and underlying implementations systematically shape the mental models and decision-making behavior of intelligent agents. Specifically, we present the first large-scale study of description-code inconsistency in the MCP ecosystem. We design an automated static analysis framework and apply it to 10,240 real-world MCP Servers across 36 categories. Our results show that while most servers are highly consistent, approximately 13% exhibit substantial mismatches that can enable undocumented privileged operations, hidden state mutations, or unauthorized financial actions. We further observe systematic differences across application categories, popularity levels, and MCP marketplaces. Our findings demonstrate that description-code inconsistency is a concrete and prevalent attack surface in MCP-based AI agents, and motivate the need for systematic auditing and stronger transparency guarantees in future agent ecosystems.

cs.CR↗

arXiv2025

"MCP Does Not Stand for Misuse Cryptography Protocol": Uncovering Cryptographic Misuse in Model Context Protocol at Scale

The Model Context Protocol (MCP) is rapidly emerging as the middleware for LLM-based applications, offering a standardized interface for tool integration. However, its built-in security mechanisms are minimal: while schemas and declarations prevent malformed requests, MCP provides no guarantees of authenticity or confidentiality, forcing developers to implement cryptography themselves. Such ad hoc practices are historically prone to misuse, and within MCP they threaten sensitive data and services. We present MICRYSCOPE, the first domain-specific framework for detecting cryptographic misuses in MCP implementations. MICRYSCOPE combines three key innovations: a cross-language intermediate representation that normalizes cryptographic APIs across diverse ecosystems, a hybrid dependency analysis that uncovers explicit and implicit function relationships (including insecure runtime compositions orchestrated by LLMs) and a taint-based misuse detector that tracks sensitive data flows and flags violations of established cryptographic rules. Applying MICRYSCOPE to 9,403 MCP servers, we identified 720 with cryptographic logic, of which 19.7% exhibited misuses. These flaws are concentrated in certain markets (e.g., Smithery Registry with 42% insecure servers), languages (Python at 34% misuse rate), and categories (Developer Tools and Data Science & ML accounting for over 50% of all misuses). Case studies reveal real-world consequences, including leaked API keys, insecure DES/ECB tools, and MD5-based authentication bypasses. Our study establishes the first ecosystem-wide view of cryptographic misuse in MCP and provides both tools and insights to strengthen the security foundations of this rapidly growing protocol.

cs.CR↗

arXiv2025

What You Code Is What We Prove: Translating BLE App Logic into Formal Models with LLMs for Vulnerability Detection

The application layer of Bluetooth Low Energy (BLE) is a growing source of security vulnerabilities, as developers often neglect to implement critical protections such as encryption, authentication, and freshness. While formal verification offers a principled way to check these properties, the manual effort of constructing formal models makes it impractical for large-scale analysis. This paper introduces a key insight: BLE application security analysis can be reframed as a semantic translation problem, i.e., from real-world code to formal models. We leverage large language models (LLMs) not to directly detect vulnerabilities, but to serve as translators that convert BLE-specific code into process models verifiable by tools like ProVerif. We implement this idea in VerifiaBLE, a system that combines static analysis, prompt-guided LLM translation, and symbolic verification to check three core security features: encryption, randomness, and authentication. Applied to 1,050 Android BLE apps, VerifiaBLE uncovers systemic weaknesses: only 10.2\% of apps implement all three protections, while 53.9\% omit them entirely. Our work demonstrates that using LLMs as structured translators can lower the barrier to formal methods, unlocking scalable verification across security-critical domains.

cs.CR↗

arXiv2024

On Protecting the Data Privacy of Large Language Models (LLMs): A Survey

Large language models (LLMs) are complex artificial intelligence systems capable of understanding, generating and translating human language. They learn language patterns by analyzing large amounts of text data, allowing them to perform writing, conversation, summarizing and other language tasks. When LLMs process and generate large amounts of data, there is a risk of leaking sensitive information, which may threaten data privacy. This paper concentrates on elucidating the data privacy concerns associated with LLMs to foster a comprehensive understanding. Specifically, a thorough investigation is undertaken to delineate the spectrum of data privacy threats, encompassing both passive privacy leakage and active privacy attacks within LLMs. Subsequently, we conduct an assessment of the privacy protection mechanisms employed by LLMs at various stages, followed by a detailed examination of their efficacy and constraints. Finally, the discourse extends to delineate the challenges encountered and outline prospective directions for advancement in the realm of LLM privacy protection.

cs.CR↗

arXiv2024

FedRFQ: Prototype-Based Federated Learning with Reduced Redundancy, Minimal Failure, and Enhanced Quality

Federated learning is a powerful technique that enables collaborative learning among different clients. Prototype-based federated learning is a specific approach that improves the performance of local models under non-IID (non-Independently and Identically Distributed) settings by integrating class prototypes. However, prototype-based federated learning faces several challenges, such as prototype redundancy and prototype failure, which limit its accuracy. It is also susceptible to poisoning attacks and server malfunctions, which can degrade the prototype quality. To address these issues, we propose FedRFQ, a prototype-based federated learning approach that aims to reduce redundancy, minimize failures, and improve \underline{q}uality. FedRFQ leverages a SoftPool mechanism, which effectively mitigates prototype redundancy and prototype failure on non-IID data. Furthermore, we introduce the BFT-detect, a BFT (Byzantine Fault Tolerance) detectable aggregation algorithm, to ensure the security of FedRFQ against poisoning attacks and server malfunctions. Finally, we conduct experiments on three different datasets, namely MNIST, FEMNIST, and CIFAR-10, and the results demonstrate that FedRFQ outperforms existing baselines in terms of accuracy when handling non-IID data.

cs.DC↗