Artifacts: When AIOps Become "AI Oops": Subverting LLM-driven IT Operations via Telemetry Manipulation
Open accessAbstract
Artifacts for the paper: When AIOps Become "AI Oops": Subverting LLM-driven IT Operations via Telemetry Manipulation Table of Contents ./logs/ contains logs for the attack runs. ./AIOpsDoom/ contains the code that implements AIOpsDoom. ./AIOpsShield/ contains the code that implements AIOpsShield. Each directory contains a README that covers the specific artifact.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
NetOps rewards agentic systems that are tool-first and verification-first, rather than conversationally fluent.
“In other words, NetOps rewards agentic systems that are tool-first and verification-first, rather than conversationally fluent [1], [3], [101], [110].”
From Large language models for agentic NetOps and AIOps: Architectures, evaluation, and safety (2027) · cites this paper as [101]
- Authors
- Pasquini, D., & Efstathopoulos, P.
- Affiliations
- RSAC Labs
- Venue
- Zenodo
- Publisher
- Zenodo
- Published
- 2025-12-16
- OpenAlex
- W7115678150
- Cited by
- 0
- References
- 0
- Type
- software
- Language
- en
- Open access
- green
- doi.org
- Locations
- Zenodo (CERN European Organization for Nuclear Research)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Physical Sciences › Computer Science › Computer Networks and Communications › Software System Performance and Reliability
- Physical Sciences › Computer Science › Computer Networks and Communications › Network Security and Intrusion Detection
- Keywords
- AIOps, large language models
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
