AgentTrace: Execution-Level Fingerprinting of Black-Box LLM Agents

Reported by arXiv cs.CR (Gejian Zhao, Hanzhou Wu, Xinpeng Zhang)

Summary by Cyber Security News26 Oct 2026, 05:00 CET

About this summary. This is a short excerpt from the description that arXiv cs.CR published with its article. Cyber Security News did not report or verify the underlying story. Read the original: https://arxiv.org/abs/2610.32092

arXiv:2610.32092v1 Announce Type: new 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. We propose AgentTrace, an active framework that identifies the foundation model behind a black-box agent via observable execution traces.

Read the full article at arXiv cs.CR →

Source attribution: headline and facts are from arXiv cs.CR (arxiv.org). Summary method: excerpt of the source description. See our source attribution policy.

Related coverage

Hacking on Autopilot: Inside ARTEX Cybercrime Campaigns

ARTEX AI Pentest Tool: What Security Teams Need to Know

🏴☠️ Thegentlemen has just published a new victim : RedBlink Technologies

When File Ingestion Misleads Language Models: Measuring and Mitigating Divergences in Office Documents

A Hybrid Approach for Automated Security Pattern Recovery

Enforcing Accountable Disclosure in Confidential AI