Skip to content
Apart Research
Apart Research
Contact us
Sprint projectSep 14, 2026Paris

Correlating Weak Signals Paged a Synthetic Agentic Intrusion Before Any Secret Was Read

Yassine Bentayfor · Team Signal Before Severity

Submitted to AI Incident Response Sprint. Sprint projects are early-stage work by participants, not Apart Research publications.

Read the report

Report: Correlating Weak Signals Paged a Synthetic Agentic Intrusion Before Any Secret Was Read

Open in a new tab (opens in new tab)
Code (opens in new tab)
Share

AgentPage is an auditable, sequence aware paging detector for machine speed AI incidents. It correlates distinct suspicious telemetry categories on one host within a sliding window, allowing weak signals to trigger escalation before any single event becomes severe. I compared it with critical only, high severity, and rate only baselines across three canonical synthetic streams and 90 deterministic variants. AgentPage detected all 30 constructed intrusions and paged 106 seconds earlier on average than high severity paging, before secret access in every attack variant. This gain caused six false pages among 60 benign variants. Ablations showed that category deduplication prevents repeated alerts from impersonating independent evidence, while the diversity bonus creates both the earlier warning and its false page cost. The code, data, tests, figures, and results are fully reproducible.

Reviews

Judging this Sprint?

Review this project

Your public critique appears on this page without your name. Your private critique is not published; only the Apart team reads it. If you agree below, we share your review with grantmaking.ai (opens in new tab) and the Transformative AI Fund so strong projects can be funded.

Not shown on this page.

Shown on this page, without your name.

Only the Apart team reads this, and funders if you agree below.

Share my name publicly on grantmaking.ai *
Share my private critique with funders *

How much would this matter for AI safety if it worked? How innovative is it? For scores of 4-5: is this actually new to the field, or replicating recent work?

Scoring guide
  1. 1Negligible. No clear problem addressed, or no meaningful novelty.
  2. 2Limited. Addresses a real problem but with a generic or well-trodden approach. Incremental at best.
  3. 3Moderate. Clear problem with a reasonable approach; some novelty in framing or method beyond routine application of existing tools.
  4. 4Significant. Important problem with an original approach, or identifies a neglected problem area. A valuable contribution others could build on.
  5. 5Exceptional. Tackles a critical AI safety problem with a genuinely novel approach, or opens a new research direction. Clear theory of change. You'd be excited to share this with researchers in the area.

How sound are methodology, implementation, and findings?

Scoring guide
  1. 1Seriously flawed. Methodology broken, results uninterpretable, or implementation doesn't work.
  2. 2Weak. Approach has significant gaps: missing validation, flawed experimental design, or incomplete implementation.
  3. 3Competent. Technically solid given the short duration. Methodology makes sense, results are interpretable, limitations acknowledged, work builds toward clear conclusions.
  4. 4Strong. Thorough methodology with convincing validation. Results clearly support conclusions. Immediately useful for future work.
  5. 5Exceptional. Ambitious scope executed rigorously. Surprising findings, novel methods, or unusually robust validation.

How clearly are work, findings, and impact potential communicated?

Scoring guide
  1. 1Incomprehensible. Cannot determine what the project is actually claiming or doing.
  2. 2Hard to follow. Key information buried, missing, or diluted by excessive length. Significant effort to extract main points.
  3. 3Clear enough. Can understand the problem, approach, and results without undue effort. Core content clearly present: problem, method, findings, limitations.
  4. 4Well presented. Easy to follow, well-structured, appropriate level of detail. Target audience would get it quickly.
  5. 5Exceptionally clear. A pleasure to read. Complex ideas made accessible. Could serve as a model for how to present this type of work.

  1. The main gap is positioning. This is risk-based alerting, and Splunk Enterprise Security ships both key mechanisms as default correlation searches — "ATT&CK Tactic Threshold Exceeded" fires on tactic_count >= 3 AND source_count >= 4, which is the diversity bonus, and dc(tactic) is category deduplication. Sentinel, Exabeam, and Chronicle have equivalents. No related work engages with any of it, so a reader from a SOC will see apparent reinvention.

    Both headline metrics are constructed. TPR 1.000 is guaranteed by scenario design; FPR 0.100 is the fraction of benign variants deliberately built to be hard; the 106 seconds depends on where severity labels were placed. The limitations acknowledge the general problem but should connect it to these specific numbers.

  2. The paper tackles the right gap: in the real incident the signals were correlated but nobody was paged. The ablations are honest and they show the diversity bonus causes both the 106-second gain and all six false pages, and that the rate bonus does nothing.

Cite this project

@misc{bentayfor2026correlating,
  title = {{Correlating Weak Signals Paged a Synthetic Agentic Intrusion Before Any Secret Was Read}},
  author = {Yassine Bentayfor},
  year = {2026},
  month = sep,
  note = {Submitted to AI Incident Response Sprint, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/correlating-weak-signals-paged-a-synthetic-agentic-intrusion-before-any-secret-was-read-flwi}},
  url = {https://apartresearch.com/sprints/projects/correlating-weak-signals-paged-a-synthetic-agentic-intrusion-before-any-secret-was-read-flwi}
}

More from AI Incident Response Sprint

All 233 entriesBrowse all projects

Build something like this at the next Sprint

AI Collusion Research Sprint · Oct 23 - 25, 2026