Cross-LLM Generalization of Behavioral Backdoor Detection in AI Agent Supply Chains

Reading time: 2 minute
...

📝 Original Info

  • Title: Cross-LLM Generalization of Behavioral Backdoor Detection in AI Agent Supply Chains
  • ArXiv ID: 2511.19874
  • Date: 2025-11-25
  • Authors: ** 논문에 명시된 저자 정보가 제공되지 않았습니다. (저자명 및 소속을 확인하려면 원문을 참고하시기 바랍니다.) — **

📝 Abstract

As AI agents become integral to enterprise workflows, their reliance on shared tool libraries and pre-trained components creates significant supply chain vulnerabilities. While previous work has demonstrated behavioral backdoor detection within individual LLM architectures, the critical question of cross-LLM generalization remains unexplored, a gap with serious implications for organizations deploying multiple AI systems. We present the first systematic study of cross-LLM behavioral backdoor detection, evaluating generalization across six production LLMs (GPT-5.1, Claude Sonnet 4.5, Grok 4.1, Llama 4 Maverick, GPT-OSS 120B, and DeepSeek Chat V3.1). Through 1,198 execution traces and 36 cross-model experiments, we quantify a critical finding: single-model detectors achieve 92.7% accuracy within their training distribution but only 49.2% across different LLMs, a 43.4 percentage point generalization gap equivalent to random guessing. Our analysis reveals that this gap stems from model-specific behavioral signatures, particularly in temporal features (coefficient of variation > 0.8), while structural features remain stable across architectures. We show that model-aware detection incorporating model identity as an additional feature achieves 90.6% accuracy universally across all evaluated models. We release our multi-LLM trace dataset and detection framework to enable reproducible research.

💡 Deep Analysis

📄 Full Content

Reference

This content is AI-processed based on open access ArXiv data.

Start searching

Enter keywords to search articles

↑↓
ESC
⌘K Shortcut