Skip to content
Apart Research
Apart Research
Contact us
Sprint projectJul 27, 2026Tel Aviv-Yafo

HuggingThreat: A Community Platform for Secret-Loyalty Artifact Discovery, Adversarial Auditing, and Threat Intelligence

Lihi Shalmon · Team HuggingThreat

Submitted to Secret Loyalties Hackathon. Sprint projects are early-stage work by participants, not Apart Research publications.

Read the report

Report: HuggingThreat: A Community Platform for Secret-Loyalty Artifact Discovery, Adversarial Auditing, and Threat Intelligence

Open in a new tab (opens in new tab)
Code (opens in new tab)More on hugging-threats.org (opens in new tab)
Share

HuggingThreat is a community-powered intelligence and detection platform for investigating secret loyalties across the open AI ecosystem on Hugging Face—including concealed objectives, allegiances, and behaviors that may evade standard evaluations. The platform connects model organisms, detection methods, community reports, lineage, and versioned evidence in one shared workflow. Researchers can run or request adversarial assessments, compare results, and build on prior work instead of repeating costly, isolated tests. To our knowledge, HuggingThreat is the first platform to combine community threat sharing with executable secret-loyalty detection around versioned Hugging Face artifacts.

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. Thank you for this great submission! Very intrigued by the idea, and absolutely useful for encouraging a shared corpus on research artifacts on AI Safety threats, such as Secret Loyalties. Good shout, too, on the dual-use considerations – I'd love for you to dive further into possible mitigations, e.g. via researcher verification as used in biosecurity. Would be great to put together a screenshot slidedeck or video for your demo to let your prototype shine!

  2. The paper keeps suggesting that a prototype exists, but the link provided is dead. It would have been nice to see a working demo, even if the demo was built on some mock data. These kinds of proposals that are of the shape of "platform that crowdsources info" are easy to propose but a lot of leg work and hustle has to go into execution, and I couldn't find evidence of special insight into what would make such a platform work, or any automated methods that could be deployed on a wide scale.

Cite this project

@misc{shalmon2026huggingthreat,
  title = {{HuggingThreat: A Community Platform for Secret-Loyalty Artifact Discovery, Adversarial Auditing, and Threat Intelligence}},
  author = {Lihi Shalmon},
  year = {2026},
  month = jul,
  note = {Submitted to Secret Loyalties Hackathon, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/huggingthreat-a-community-platform-for-secretloyalty-artifact-discovery-adversarial-auditing-and-threat-intelligence-48ha}},
  url = {https://apartresearch.com/sprints/projects/huggingthreat-a-community-platform-for-secretloyalty-artifact-discovery-adversarial-auditing-and-threat-intelligence-48ha}
}

More from Secret Loyalties Hackathon

All 177 entriesBrowse all projects

Build something like this at the next Sprint

AI Collusion Research Sprint · Oct 23 - 25, 2026