English(EN) AgentTrace: Execution-Level Fingerprinting of Black-Box LLM Agents

AgentTrace框架以96%的准确率识别LLM代理的基础模型

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-26 04:00

研究人员开发了AgentTrace，一个旨在识别黑盒LLM代理底层基础模型的新框架。该方法通过注入触发序列化失败的探针，然后根据其时间序列和恢复行为进行分析。AgentTrace在归属方面达到了96.0%的准确率，甚至能区分Llama 3 8B和70B等相似模型，并且在对抗性提示混淆和温度缩放方面仍然有效。 AI

影响该方法通过提供一种验证LLM代理来源的方式，可以增强自主AI系统的安全性和可信度。

排序理由研究论文，详细介绍了一种识别LLM代理的新方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 13 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 研究论文，详细介绍了一种识别LLM代理的新方法。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Gejian Zhao, Hanzhou Wu, Xinpeng Zhang · 2026-10-26 04:00

AgentTrace：黑盒LLM代理的执行级指纹识别

arXiv:2610.32092v1 Announce Type: cross Abstract: Verifying the provenance of autonomous LLM agents is a critical security challenge. Existing semantic attribution is easily obfuscated by system prompts, while active watermarking conflicts with schema-constrained tool generation.…

本文如何被排名

报道来源 [1]

AgentTrace：黑盒LLM代理的执行级指纹识别

相关实体

相关话题