Skip to content
Apart Research
Apart Research
Contact us
Sprint projectOct 25, 2026Delhi, India

Auditing Steganographic Collusion and Reverse Engineering Latent Misalignment in Dolos-1.5B

Vinyas Maurya · Team Evariste`

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

Read the report

Report: Auditing Steganographic Collusion and Reverse Engineering Latent Misalignment in Dolos-1.5B

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

As I explored how language models interact in economic contexts, I became increasingly concerned about their potential to coordinate against their creators. My study focuses on the Apart Research Collusion Sprint and the challenge of red-teaming the Dolos-1.5B model. I discovered that in simple environments, models can inadvertently devise unexpected pricing strategies, whereas more complex contexts enable covert collusion. I emphasised the importance of multi-modal auditing to distinguish between genuine adaptation and deliberate deception. While testing ten collusion detection systems, I found that mutual information detectors were effective, whereas traditional linguistic analysis struggled. My analysis of Dolos-1.5B revealed that its coordination behaviour is tied to specific model layers and activated by certain Unicode shifts.

Reviews

Judging this Sprint?

Review “Auditing Steganographic Collusion and Reverse Engineering Latent Misalignment in Dolos-1.5B”

Your public critique appears on the project page without your name. Reviews of strong projects are shared with funders, as you choose below.

Not shown on the project page.

Shown on the project page, without your name.

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

Decline to score

Only when the quality of the writing makes the work impossible to follow. Say why in your private critique; the project page shows only that a judge declined, not why.

How much would this matter for the field 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 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.
Sharing your name *

When we share a strong project with funders, your name, scores and public critique go with it, confidentially; this choice is only about whether your name is public. If you think this project deserves funding, please also endorse it: that carries the most weight.

Share my private critique with funders *

See our Privacy Policy.

No public critique yet.

Cite this project

@misc{maurya2026auditing,
  title = {{Auditing Steganographic Collusion and Reverse Engineering Latent Misalignment in Dolos-1.5B}},
  author = {Vinyas Maurya},
  year = {2026},
  month = oct,
  note = {Submitted to AI Collusion Research Sprint, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/auditing-steganographic-collusion-and-reverse-engineering-latent-misalignment-in-dolos15b-zp9y}},
  url = {https://apartresearch.com/sprints/projects/auditing-steganographic-collusion-and-reverse-engineering-latent-misalignment-in-dolos15b-zp9y}
}

More from AI Collusion Research Sprint

All 394 entriesBrowse all projects

A Sprint is running now

AI Collusion Research Sprint · Oct 23 - 25, 2026