Metraipolis › archive › dc_343e3bd2b173

APTInvestBench: Evaluating Autonomous APT Investigation under Varying Telemetry — arXiv:2609.38954

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.38954
License (as archived)
CC0-1.0
Archived
2026-10-07T12:44:38.070Z
SHA-256 of the archived text
d8bad892749f16df770abf9cd5e864c1b96685224581b4aa08e76967fd8e4715
Stable URL of this page
https://metraipolis.com/documento/dc_343e3bd2b173

How to cite

APTInvestBench: Evaluating Autonomous APT Investigation under Varying Telemetry — arXiv:2609.38954 — arXiv (en), https://arxiv.org/abs/2609.38954 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_343e3bd2b173 (Metraipolis archive dc_343e3bd2b173, sha256 d8bad892749f16df770abf9cd5e864c1b96685224581b4aa08e76967fd8e4715)
BibTeX
@misc{dc343e3bd2b173,
  title = {APTInvestBench: Evaluating Autonomous APT Investigation under Varying Telemetry — arXiv:2609.38954},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.38954},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_343e3bd2b173; sha256 d8bad892749f16df770abf9cd5e864c1b96685224581b4aa08e76967fd8e4715},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38954. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language model (LLM) agents could help security operations centers (SOCs) investigate advanced persistent threats (APTs) by turning weak leads into evidence for intrusion scoping and response. Yet success under one telemetry setting does not establish robustness to changes in log collection, retention, or sampling. We introduce APTInvestBench, a benchmark for evaluating cross-telemetry robustness in autonomous APT investigation. It comprises 370 cases across seven SOC-inspired conditions, derived from 56 report-informed attack reconstructions with 16.4 million log records. Agents investigate unverified leads and submit reports with record-level citations. Fixed action-level support requirements track sufficient evidence across available logs, query returns, and formal citations, separating telemetry limitations from acquisition and reporting gaps. Across eleven LLMs, agents acquire sufficient evidence for 44.3% of recoverable attack actions on average, while formal citations support only 25.0%. More importantly, aggregate coverage can conceal substantial instability: from Full to endpoint-only telemetry, coverage declines by only 1.6 percentage points, yet 35.5% of previously covered actions lose sufficient citation support despite remaining recoverable. Across four frameworks, such losses persist even when registered supporting records remain unchanged. APTInvestBench provides reusable investigation environments and diagnostic evaluation for identifying these gaps and developing more reliable defensive agents.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AI).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.38954 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T12:14:13.983Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).