works on

From the 1 of 10 linked papers with an AI index.

activity
20242026
collaborators

10 papers

cs.CR2026

MCP Pitfall Lab: Exposing Developer Pitfalls in MCP Tool Server Security under Multi-Vector Attacks

Run Hao, Zhuoran Tan

The paper introduces MCP Pitfall Lab, a security testing framework for Model Context Protocol tool servers that identifies common developer mistakes and evaluates attacks using pro…

cs.CR2026

MCP-SandboxScan: WASM-based Secure Execution and Runtime Analysis for MCP Tools

Zhuoran Tan, Run Hao, Jeremy Singer +2

Tool-augmented Large Language Model (LLM) agents create a new supply-chain surface: Model Context Protocol (MCP) tools are installed like third-party packages, yet their outputs ca…

cs.CR2026

FuseChain: Runtime Evidence Reconstruction for Software Supply-Chain Attacks

Zhuoran Tan, Yutian Tang, Jeremy Singer +2

Software supply-chain (SSC) attacks are increasingly multi-stage, cross-source, and temporally distributed. A single attack campaign may leave weak and fragmented traces across mul…

cs.CR2026

Operational Runtime Behavior Mining for Open-Source Supply Chain Security

Zhuoran Tan, Ke Xiao, Jeremy Singer +1

Open-source software (OSS) is a critical component of modern software systems, yet supply chain security remains challenging in practice due to unavailable or obfuscated source cod…

cs.CR2026

Attesting LLM Pipelines: Enforcing Verifiable Training and Release Claims

Zhuoran Tan, Jeremy Singer, Christos Anagnostopoulos

Modern Large Language Model (LLM) systems are assembled from third-party artifacts such as pre-trained weights, fine-tuning adapters, datasets, dependency packages, and container i…

cs.CR2026

SynthChain: A Synthetic Benchmark and Forensic Analysis of Advanced and Stealthy Software Supply Chain Attacks

Zhuoran Tan, Wenbo Guo, Taylor Brierley +3

Advanced software supply chain (SSC) attacks are increasingly runtime-only and leave fragmented evidence across hosts, services, and build/dependency layers, so any single telemetr…