Metraipolis › archive › dc_facd21e94c53

Topological Attribution Distance (TAD): Revealing Segment-Level RAG Influence on LLM Output Geometry for Incident Log Analysis — arXiv:2608.16775

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.16775
License (as archived)
CC0-1.0
Archived
2026-10-18T18:07:31.679Z
SHA-256 of the archived text
45afbb1eb71dfdba7e6b8b9f712be509912f67354392b1db7e2d9cc4f291ace1
Stable URL of this page
https://metraipolis.com/documento/dc_facd21e94c53

How to cite

Topological Attribution Distance (TAD): Revealing Segment-Level RAG Influence on LLM Output Geometry for Incident Log Analysis — arXiv:2608.16775 — arXiv (en), https://arxiv.org/abs/2608.16775 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_facd21e94c53 (Metraipolis archive dc_facd21e94c53, sha256 45afbb1eb71dfdba7e6b8b9f712be509912f67354392b1db7e2d9cc4f291ace1)
BibTeX
@misc{dcfacd21e94c53,
  title = {Topological Attribution Distance (TAD): Revealing Segment-Level RAG Influence on LLM Output Geometry for Incident Log Analysis — arXiv:2608.16775},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16775},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_facd21e94c53; sha256 45afbb1eb71dfdba7e6b8b9f712be509912f67354392b1db7e2d9cc4f291ace1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16775. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large Language Models (LLMs) are increasingly being deployed in cybersecurity operations to assist cybersecurity analysts with rapid decision-making against emerging threats. However, there is a main criteria that must be met when using LLMs in cybersecurity, that is, trust in the generated outputs. As Agentic AI is integrated into operational systems, a robust evidence attribution and provenance tracking technique is essential to trace the origins of model generations. When autonomous agents make a decision (right or wrong), the ability to trace back through the decision chain is critical, as without it, teams cannot identify which segment of the data caused the model generation. Existing methods often struggle to distinguish among complex and highly similar evidence sources, such as cyber incident logs. This reveals a key gap: current approaches do not adequately capture the holistic geometric relationship between the retrieved evidence and the generated response for reliable evidence verification. To bridge this gap, we propose Topological Attribution Distance (TAD), inspired by Topology, to characterize and capture the global geometric shape of an output and its changes against its retrieved logs. In other words, if the embeddings of a specific source log drastically changes the geometry of the model's response in the embedding space, this suggests that such log is a critical source for the model's generated response. Therefore, TAD is powered by segment-level ablation attribution to investigate incident logs of an actual cyberattack. We demonstrate how TAD finds the most attributed logs on LLM outputs in an adaptive manner. This can provide an explainable and trustworthy tracing based on each LLM's hidden state to understand how geometrically different retrieved logs influence the model generation, and provide evidence verification in cybersecurity and Agentic-AI workflows.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.16775 — 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 2026-10-18T16:29:14.152Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).